papers

Publications (174)

cs.CL2018

Simple Unsupervised Keyphrase Extraction using Sentence Embeddings

Kamil Bennani-Smires, Claudiu Musat, Andreea Hossmann +2

Keyphrase extraction is the task of automatically selecting a small set of phrases that best describe a given free text document. Supervised keyphrase extraction requires large amo…

cs.CY2024

Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants

Beatriz Borges, Negar Foroutan, Deniz Bayazit +87

AI assistants are being increasingly used by students enrolled in higher education institutions. While these tools provide opportunities for improved teaching and education, they a…

cs.LG2023

Byzantine-Robust Decentralized Learning via ClippedGossip

Lie He, Sai Praneeth Karimireddy, Martin Jaggi

In this paper, we study the challenging task of Byzantine-robust decentralized training on arbitrary communication graphs. Unlike federated learning where workers communicate throu…

cs.LG2017

Faster Coordinate Descent via Adaptive Importance Sampling

Dmytro Perekrestenko, Volkan Cevher, Martin Jaggi

Coordinate descent methods employ random partial updates of decision variables in order to solve huge-scale convex optimization problems. In this work, we introduce new adaptive ru…

cs.LG2021

Exact Optimization of Conformal Predictors via Incremental and Decremental Learning

Giovanni Cherubin, Konstantinos Chatzikokolakis, Martin Jaggi

Conformal Predictors (CP) are wrappers around ML models, providing error guarantees under weak assumptions on the data distribution. They are suitable for a wide range of problems,…

cs.LG2017

A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe

Francesco Locatello, Rajiv Khanna, Michael Tschannen +1

Two of the most fundamental prototypes of greedy optimization are the matching pursuit and Frank-Wolfe algorithms. In this paper, we take a unified view on both classes of methods,…

stat.ML2021

Taming GANs with Lookahead-Minmax

Tatjana Chavdarova, Matteo Pagliardini, Sebastian U. Stich +2

Generative Adversarial Networks are notoriously challenging to train. The underlying minmax optimization is highly susceptible to the variance of the stochastic gradient and the ro…

cs.LG2020

PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning

Thijs Vogels, Sai Praneeth Karimireddy, Martin Jaggi

Lossy gradient compression has become a practical tool to overcome the communication bottleneck in centrally coordinated distributed training of machine learning models. However, a…

cs.LG2020

Sparse Communication for Training Deep Networks

Negar Foroutan Eghlidi, Martin Jaggi

Synchronous stochastic gradient descent (SGD) is the most common method used for distributed training of deep learning models. In this algorithm, each worker shares its local gradi…

cs.CL2020

Robust Cross-lingual Embeddings from Parallel Sentences

Ali Sabet, Prakhar Gupta, Jean-Baptiste Cordonnier +2

Recent advances in cross-lingual word embeddings have primarily relied on mapping-based methods, which project pretrained word embeddings from different languages into a shared spa…

cs.LG2025

-LoRA: Effective Fine-Tuning via Base Model Rescaling

Aymane El Firdoussi, El Mahdi Chayti, Mohamed El Amine Seddik +1

Fine-tuning has proven to be highly effective in adapting pre-trained models to perform better on new desired tasks with minimal data samples. Among the most widely used approaches…

cs.CL2024

DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging

Matteo Pagliardini, Amirkeivan Mohtashami, Francois Fleuret +1

The transformer architecture by Vaswani et al. (2017) is now ubiquitous across application domains, from natural language processing to speech processing and image understanding. W…

cs.CL2023

Irreducible Curriculum for Language Model Pretraining

Simin Fan, Martin Jaggi

Automatic data selection and curriculum design for training large language models is challenging, with only a few existing methods showing improvements over standard training. Furt…

cs.CL2022

SKILL: Structured Knowledge Infusion for Large Language Models

Fedor Moiseev, Zhe Dong, Enrique Alfonseca +1

Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks. However, it is largely unexplored whether they can better inter…

cs.LG2021

Understanding Memorization from the Perspective of Optimization via Efficient Influence Estimation

Futong Liu, Tao Lin, Martin Jaggi

Over-parameterized deep neural networks are able to achieve excellent training accuracy while maintaining a small generalization error. It has also been found that they are able to…

cs.LG2020

Secure Byzantine-Robust Machine Learning

Lie He, Sai Praneeth Karimireddy, Martin Jaggi

Increasingly machine learning systems are being deployed to edge servers and devices (e.g. mobile phones) and trained in a collaborative manner. Such distributed/federated/decentra…

cs.LG2024

QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci +6

We introduce QuaRot, a new Quantization scheme based on Rotations, which is able to quantize LLMs end-to-end, including all weights, activations, and KV cache in 4 bits. QuaRot rot…

cs.LG2024

Deep Grokking: Would Deep Neural Networks Generalize Better?

Simin Fan, Razvan Pascanu, Martin Jaggi

Recent research on the grokking phenomenon has illuminated the intricacies of neural networks' training dynamics and their generalization behaviors. Grokking refers to a sharp rise…

cs.LG2021

Optimal Model Averaging: Towards Personalized Collaborative Learning

Felix Grimberg, Mary-Anne Hartley, Sai P. Karimireddy +1

In federated learning, differences in the data or objectives between the participating nodes motivate approaches to train a personalized machine learning model for each node. One s…

cs.LG2023

Model Fusion via Optimal Transport

Sidak Pal Singh, Martin Jaggi

Combining different models is a widely used paradigm in machine learning applications. While the most common approach is to form an ensemble of models and average their individual…

math.OC2026

A Split-Client Approach to Second-Order Optimization

El Mahdi Chayti, Martin Jaggi

Second-order optimization methods offer superior convergence rates but are often bottlenecked by the wall-clock cost of Hessian computation and factorization. In the moderate-dimen…

cs.CL2026

Enhancing Multilingual LLM Pretraining with Model-Based Data Selection

Bettina Messmer, Vinko Sabolčec, Martin Jaggi

Dataset curation has become a basis for strong large language model (LLM) performance. While various rule-based filtering heuristics exist for English and multilingual datasets, mo…

cs.LG2025

Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains

Ashok Vardhan Makkuva, Marco Bondaschi, Adway Girish +4

Attention-based transformers have achieved tremendous success across a variety of disciplines including natural languages. To deepen our understanding of their sequential modeling…

cs.LG2025

Effective Interplay between Sparsity and Quantization: From Theory to Practice

Simla Burcu Harma, Ayan Chakraborty, Elizaveta Kostenok +8

The increasing size of deep neural networks (DNNs) necessitates effective model compression to reduce their computational and memory footprints. Sparsity and quantization are two p…

cs.PF2020

On Linear Learning with Manycore Processors

Eliza Wszola, Celestine Mendler-Dünner, Martin Jaggi +1

A new generation of manycore processors is on the rise that offers dozens and more cores on a chip and, in a sense, fuses host processor and accelerator. In this paper we target th…

cs.LG2019

Evaluating the Search Phase of Neural Architecture Search

Kaicheng Yu, Christian Sciuto, Martin Jaggi +2

Neural Architecture Search (NAS) aims to facilitate the design of deep networks for new tasks. Existing techniques rely on two stages: searching over the architecture space and val…

cs.LG2022

Characterizing & Finding Good Data Orderings for Fast Convergence of Sequential Gradient Methods

Amirkeivan Mohtashami, Sebastian Stich, Martin Jaggi

While SGD, which samples from the data with replacement is widely studied in theory, a variant called Random Reshuffling (RR) is more common in practice. RR iterates through random…

cs.LG2018

Sparsified SGD with Memory

Sebastian U. Stich, Jean-Baptiste Cordonnier, Martin Jaggi

Huge scale machine learning problems are nowadays tackled by distributed optimization algorithms, i.e. algorithms that leverage the compute power of many devices for training. The…

cs.CL2017

Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification

Jan Deriu, Aurelien Lucchi, Valeria De Luca +5

This paper presents a novel approach for multi-lingual sentiment classification in short texts. This is a challenging task as the amount of training data in languages other than En…

cs.CL2025

TiMoE: Time-Aware Mixture of Language Experts

Robin Faro, Dongyang Fan, Tamar Alphaidze +1

Large language models (LLMs) are typically trained on fixed snapshots of the web, which means that their knowledge becomes stale and their predictions risk temporal leakage: relyin…

cs.LG2024

DoGE: Domain Reweighting with Generalization Estimation

Simin Fan, Matteo Pagliardini, Martin Jaggi

The coverage and composition of the pretraining data significantly impacts the generalization ability of Large Language Models (LLMs). Despite its importance, recent LLMs still rel…

cs.LG2019

Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication

Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi

We consider decentralized stochastic optimization with the objective function (e.g. data samples for machine learning task) being distributed over machines that can only commun…

cs.CL2021

Obtaining Better Static Word Embeddings Using Contextual Embedding Models

Prakhar Gupta, Martin Jaggi

The advent of contextual word embeddings -- representations of words which incorporate semantic and syntactic information from their context -- has led to tremendous improvements o…

cs.LG2023

Provably Personalized and Robust Federated Learning

Mariel Werner, Lie He, Michael Jordan +2

Identifying clients with similar objectives and learning a model-per-cluster is an intuitive and interpretable approach to personalization in federated learning. However, doing so…

cs.LG2021

Consensus Control for Decentralized Deep Learning

Lingjing Kong, Tao Lin, Anastasia Koloskova +2

Decentralized training of deep learning models enables on-device learning over networks, as well as efficient scaling to large compute clusters. Experiments in earlier works reveal…

cs.LG2020

Optimizer Benchmarking Needs to Account for Hyperparameter Tuning

Prabhu Teja Sivaprasad, Florian Mai, Thijs Vogels +2

The performance of optimizers, particularly in deep learning, depends considerably on their chosen hyperparameter configuration. The efficacy of optimizers is often studied under n…

cs.LG2020

On the Relationship between Self-Attention and Convolutional Layers

Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi

Recent trends of incorporating attention mechanisms in vision have led researchers to reconsider the supremacy of convolutional layers as a primary building block. Beyond helping C…

cs.CL2019

Interpretable Structure-aware Document Encoders with Hierarchical Attention

Khalil Mrini, Claudiu Musat, Michael Baeriswyl +1

We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentence…

cs.LG2022

RelaySum for Decentralized Deep Learning on Heterogeneous Data

Thijs Vogels, Lie He, Anastasia Koloskova +4

In decentralized machine learning, workers compute model updates on their local data. Because the workers only communicate with few neighbors without central coordination, these up…

cs.LG2021

Learning from History for Byzantine Robust Optimization

Sai Praneeth Karimireddy, Lie He, Martin Jaggi

Byzantine robustness has received significant attention recently given its importance for distributed and federated learning. In spite of this, we identify severe flaws in existing…

cs.CL2019

Crosslingual Document Embedding as Reduced-Rank Ridge Regression

Martin Josifoski, Ivan S. Paskov, Hristo S. Paskov +2

There has recently been much interest in extending vector-based word representations to multiple languages, such that words can be compared across languages. In this paper, we shif…

cs.LG2018

A Distributed Second-Order Algorithm You Can Trust

Celestine Dünner, Aurelien Lucchi, Matilde Gargiani +3

Due to the rapid growth of data and computational resources, distributed optimization has become an active research area in recent years. While first-order methods seem to dominate…

cs.LG2019

MLSys: The New Frontier of Machine Learning Systems

Alexander Ratner, Dan Alistarh, Gustavo Alonso +66

Machine learning (ML) techniques are enjoying rapidly increasing adoption. However, designing and implementing the systems that support ML models in real-world deployments remains…

cs.LG2026

Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping

Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger +2

Looped Transformers, which repeatedly apply a shared transformer block, are an architecturally natural fit for variable-length algorithmic tasks. Although they can exhibit strong l…

cs.LG2020

Unsupervised Scalable Representation Learning for Multivariate Time Series

Jean-Yves Franceschi, Aymeric Dieuleveut, Martin Jaggi

Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this…

cs.LG2026

Local MixVR: Breaking the Communication-Sample Dependence in Distributed Learning

Tehila Dahan, Bassel Hamoud, Roie Reshef +2

Communication overhead is a crucial bottleneck in scalable distributed learning. While existing methods aim to efficiently utilize data points, such as Local SGD, Minibatch SGD, an…

cs.LG2024

Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations

Alexander Hägele, Elie Bakouch, Atli Kosson +3

Scale has become a main ingredient in obtaining strong machine learning models. As a result, understanding a model's scaling properties is key to effectively designing both the rig…

math.OC2022

Linearly Convergent Frank-Wolfe with Backtracking Line-Search

Fabian Pedregosa, Geoffrey Negiar, Armin Askari +1

Structured constraints in Machine Learning have recently brought the Frank-Wolfe (FW) family of algorithms back in the spotlight. While the classical FW algorithm has poor local co…

cs.LG2022

Scalable Collaborative Learning via Representation Sharing

Frédéric Berdoz, Abhishek Singh, Martin Jaggi +1

Privacy-preserving machine learning has become a key conundrum for multi-party artificial intelligence. Federated learning (FL) and Split Learning (SL) are two frameworks that enab…

cs.LG2022

Modular Clinical Decision Support Networks (MoDN) -- Updatable, Interpretable, and Portable Predictions for Evolving Clinical Environments

Cécile Trottet, Thijs Vogels, Martin Jaggi +1

Data-driven Clinical Decision Support Systems (CDSS) have the potential to improve and standardise care with personalised probabilistic guidance. However, the size of data required…

cs.LG2024

On Convergence of Incremental Gradient for Non-Convex Smooth Functions

Anastasia Koloskova, Nikita Doikov, Sebastian U. Stich +1

In machine learning and neural network optimization, algorithms like incremental gradient, and shuffle SGD are popular due to minimizing the number of cache misses and good practic…

cs.CL2023

Controllable Topic-Focused Abstractive Summarization

Seyed Ali Bahrainian, Martin Jaggi, Carsten Eickhoff

Controlled abstractive summarization focuses on producing condensed versions of a source article to cover specific aspects by shifting the distribution of generated text towards a…

cs.LG2019

Overcoming Multi-Model Forgetting

Yassine Benyahia, Kaicheng Yu, Kamil Bennani-Smires +4

We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performan…

cs.LG2025

NeuralGrok: Accelerate Grokking by Neural Gradient Transformation

Xinyu Zhou, Simin Fan, Martin Jaggi +1

Grokking is proposed and widely studied as an intricate phenomenon in which generalization is achieved after a long-lasting period of overfitting. In this work, we propose NeuralGr…

math.OC2023

Second-order optimization with lazy Hessians

Nikita Doikov, El Mahdi Chayti, Martin Jaggi

We analyze Newton's method with lazy Hessian updates for solving general possibly non-convex optimization problems. We propose to reuse a previously seen Hessian for several iterat…

cs.LG2023

Special Properties of Gradient Descent with Large Learning Rates

Amirkeivan Mohtashami, Martin Jaggi, Sebastian Stich

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effe…

cs.LG2009

A Combinatorial Algorithm to Compute Regularization Paths

Bernd Gärtner, Joachim Giesen, Martin Jaggi +1

For a wide variety of regularization methods, algorithms computing the entire solution path have been developed recently. Solution path algorithms do not only compute the solution…

cs.LG2020

Extrapolation for Large-batch Training in Deep Learning

Tao Lin, Lingjing Kong, Sebastian U. Stich +1

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fra…

cs.CL2018

Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features

Matteo Pagliardini, Prakhar Gupta, Martin Jaggi

The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (…

cs.LG2024

Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training

Atli Kosson, Bettina Messmer, Martin Jaggi

Learning Rate Warmup is a popular heuristic for training neural networks, especially at larger batch sizes, despite limited understanding of its benefits. Warmup decreases the upda…

cs.LG2015

Adding vs. Averaging in Distributed Primal-Dual Optimization

Chenxin Ma, Virginia Smith, Martin Jaggi +3

Distributed optimization methods for large-scale machine learning suffer from a communication bottleneck. It is difficult to reduce this bottleneck while still efficiently and accu…

cs.LG2026

Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors

Alexander Hägele, Alejandro Hernández-Cano, Atli Kosson +1

Modern neural network training relies on optimizers such as Adam and Muon which act on each weight matrix as a single object. Yet every weight matrix carries two distinct quantitie…

cs.LG2025

Towards Fully FP8 GEMM LLM Training at Scale

Alejandro Hernández-Cano, Dhia Garbaya, Imanol Schlag +1

Despite the significant potential of FP8 data formats for large language model (LLM) pre-training, their adoption has been limited due to challenges in maintaining stability at sca…

cs.LG2024

Layer-wise Linear Mode Connectivity

Linara Adilova, Maksym Andriushchenko, Michael Kamp +2

Averaging neural network parameters is an intuitive method for fusing the knowledge of two independent models. It is most prominently used in federated learning. If models are aver…

math.OC2016

An Optimal Affine Invariant Smooth Minimization Algorithm

Alexandre d'Aspremont, Cristóbal Guzmán, Martin Jaggi

We formulate an affine invariant implementation of the accelerated first-order algorithm in Nesterov (1983). Its complexity bound is proportional to an affine invariant regularity…

cs.CV2017

Learning Aerial Image Segmentation from Online Maps

Pascal Kaiser, Jan Dirk Wegner, Aurelien Lucchi +3

This study deals with semantic segmentation of high-resolution (aerial) images where a semantic class label is assigned to each pixel via supervised classification as a basis for a…

cs.LG2017

Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems

Celestine Dünner, Thomas Parnell, Martin Jaggi

We propose a generic algorithmic building block to accelerate training of machine learning models on heterogeneous compute systems. Our scheme allows to efficiently employ compute…

cs.LG2022

Beyond spectral gap: The role of the topology in decentralized learning

Thijs Vogels, Hadrien Hendrikx, Martin Jaggi

In data-parallel optimization of machine learning models, workers collaborate to improve their estimates of the model: more accurate gradients allow them to use larger learning rat…

cs.CL2024

Personalized Collaborative Fine-Tuning for On-Device Large Language Models

Nicolas Wagner, Dongyang Fan, Martin Jaggi

We explore on-device self-supervised collaborative fine-tuning of large language models with limited local data availability. Taking inspiration from the collaborative learning com…

cs.CR2021

Federated Learning for Malware Detection in IoT Devices

Valerian Rey, Pedro Miguel Sánchez Sánchez, Alberto Huertas Celdrán +2

This work investigates the possibilities enabled by federated learning concerning IoT malware detection and studies security issues inherent to this new learning paradigm. In this…

cs.LG2026

Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs

Thierry Bossy, Julien Vignoud, Tahseen Rabbani +2

Federated learning (FL) is a popular paradigm for collaborative training which avoids direct data exposure between clients. However, data privacy issues still remain: FL-trained la…

cs.LG2025

Stochastic Difference-of-Convex Optimization with Momentum

El Mahdi Chayti, Martin Jaggi

Stochastic difference-of-convex (DC) optimization is prevalent in numerous machine learning applications, yet its convergence properties under small batch sizes remain poorly under…

cs.LG2025

Benchmarking Optimizers for Large Language Model Pretraining

Andrei Semenov, Matteo Pagliardini, Martin Jaggi

The recent development of Large Language Models (LLMs) has been accompanied by an effervescence of novel ideas and methods to better optimize the loss of deep learning models. Clai…

cs.CL2025

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Guilherme Penedo, Hynek Kydlíček, Vinko Sabolčec +7

Pre-training state-of-the-art large language models (LLMs) requires vast amounts of clean and diverse text data. While the open development of large high-quality English pre-traini…

cs.LG2026

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference

Simla Burcu Harma, Danila Mishin, Zhengyuan Su +7

4-bit quantization enables efficient LLM inference, but suffers from significant accuracy degradation due to outliers. Prior work addresses this problem via data rotation or mixed-…

cs.CL2026

Tying the Loop -- Tied Expert Layers in Mixture-of-Experts Language Models

Martin Jaggi

Mixture-of-Experts (MoE) architectures efficiently scale Large Language Models (LLMs) by activating only a small fraction of their experts per token, yet the full parameter count -…

cs.CL2026

Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection

Yassine Turki, Vinko Sabolčec, Bettina Messmer +1

As Large Language Models (LLMs) scale, data curation has shifted from maximizing volume to optimizing the signal-to-noise ratio by performing quality filtering. However, for many l…

cs.LG2018

Global linear convergence of Newton's method without strong-convexity or Lipschitz gradients

Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi

We show that Newton's method converges globally at a linear rate for objective functions whose Hessians are stable. This class of problems includes many functions which are not str…

eess.SP2019

Forecasting intracranial hypertension using multi-scale waveform metrics

Matthias Hüser, Adrian Kündig, Walter Karlen +2

Objective: Acute intracranial hypertension is an important risk factor of secondary brain damage after traumatic brain injury. Hypertensive episodes are often diagnosed reactively,…

cs.LG2024

CoBo: Collaborative Learning via Bilevel Optimization

Diba Hashemi, Lie He, Martin Jaggi

Collaborative learning is an important tool to train multiple clients more effectively by enabling communication among clients. Identifying helpful clients, however, presents chall…

cs.LG2020

PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization

Thijs Vogels, Sai Praneeth Karimireddy, Martin Jaggi

We study gradient compression methods to alleviate the communication bottleneck in data-parallel distributed optimization. Despite the significant attention received, current compr…

cs.LG2023

Multiplication-Free Transformer Training via Piecewise Affine Operations

Atli Kosson, Martin Jaggi

Multiplications are responsible for most of the computational cost involved in neural network training and inference. Recent research has thus looked for ways to reduce the cost as…

cs.LG2021

Multi-Head Attention: Collaborate Instead of Concatenate

Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed s…

cs.LG2021

Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates

Sebastian U. Stich, Amirkeivan Mohtashami, Martin Jaggi

It has been experimentally observed that the efficiency of distributed training with stochastic gradient (SGD) depends decisively on the batch size and -- in asynchronous implement…

cs.CL2025

URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training

Dongyang Fan, Vinko Sabolčec, Martin Jaggi

Large Language Models (LLMs) are commonly pretrained on vast corpora of text without utilizing contextual metadata such as source, quality, or topic, leading to a context-free lear…

cs.LG2021

Understanding the Effects of Data Parallelism and Sparsity on Neural Network Training

Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr +1

We study two factors in neural network training: data parallelism and sparsity; here, data parallelism means processing training data in parallel using distributed systems (or equi…

cs.LG2016

Pursuits in Structured Non-Convex Matrix Factorizations

Rajiv Khanna, Michael Tschannen, Martin Jaggi

Efficiently representing real world data in a succinct and parsimonious manner is of central importance in many fields. We present a generalized greedy pursuit framework, allowing…

cs.CL2023

Landmark Attention: Random-Access Infinite Context Length for Transformers

Amirkeivan Mohtashami, Martin Jaggi

While Transformers have shown remarkable success in natural language processing, their attention mechanism's large memory requirements have limited their ability to handle longer c…

cs.LG2012

An Exponential Lower Bound on the Complexity of Regularization Paths

Bernd Gärtner, Martin Jaggi, Clément Maria

For a variety of regularized optimization problems in machine learning, algorithms computing the entire solution path have been developed recently. Most of these methods are quadra…

math.OC2014

An Affine Invariant Linear Convergence Analysis for Frank-Wolfe Algorithms

Simon Lacoste-Julien, Martin Jaggi

We study the linear convergence of variants of the Frank-Wolfe algorithms for some classes of strongly convex problems, using only affine-invariant quantities. As in Guelat & Marco…

cs.NE2024

LASER: Linear Compression in Wireless Distributed Optimization

Ashok Vardhan Makkuva, Marco Bondaschi, Thijs Vogels +3

Data-parallel SGD is the de facto algorithm for distributed optimization, especially for large scale machine learning. Despite its merits, communication bottleneck is one of its pe…

cs.CL2019

Correlating Twitter Language with Community-Level Health Outcomes

Arno Schneuwly, Ralf Grubenmann, Séverine Rion Logean +2

We study how language on social media is linked to diseases such as atherosclerotic heart disease (AHD), diabetes and various types of cancer. Our proposed model leverages state-of…

cs.DC2026

An Engineering Journey Training Large Language Models at Scale on Alps: The Apertus Experience

Jonathan Coles, Stefano Schuppli, Lukas Drescher +20

Large Language Models (LLMs) have surged as a transformative technology for science and society, prompting governments worldwide to pursue sovereign AI capabilities that ensure dat…

cs.LG2024

Towards an empirical understanding of MoE design choices

Dongyang Fan, Bettina Messmer, Martin Jaggi

In this study, we systematically evaluate the impact of common design choices in Mixture of Experts (MoEs) on validation performance, uncovering distinct influences at token and se…

cs.LG2025

DISCO: A Browser-Based Privacy-Preserving Framework for Distributed Collaborative Learning

Julien T. T. Vignoud, Valérian Rousset, Hugo El Guedj +28

Data is often impractical to share for a range of well considered reasons, such as concerns over privacy, intellectual property, and legal constraints. This not only fragments the…

cs.LG2023

FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings

Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers +21

Federated Learning (FL) is a novel approach enabling several clients holding sensitive data to collaboratively train machine learning models, without centralizing data. The cross-s…

stat.ML2019

On Matching Pursuit and Coordinate Descent

Francesco Locatello, Anant Raj, Sai Praneeth Karimireddy +4

Two popular examples of first-order optimization methods over linear spaces are coordinate descent and matching pursuit algorithms, with their randomized variants. While the former…

cs.LG2017

Approximate Steepest Coordinate Descent

Sebastian U. Stich, Anant Raj, Martin Jaggi

We propose a new selection rule for the coordinate selection in coordinate descent methods for huge-scale optimization. The efficiency of this novel scheme is provably better than…

cs.LG2024

Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks

Atli Kosson, Bettina Messmer, Martin Jaggi

This study investigates how weight decay affects the update behavior of individual neurons in deep neural networks through a combination of applied analysis and experimentation. We…

cs.LG2021

WAFFLE: Weighted Averaging for Personalized Federated Learning

Martin Beaussart, Felix Grimberg, Mary-Anne Hartley +1

In federated learning, model personalization can be a very effective strategy to deal with heterogeneous training data across clients. We introduce WAFFLE (Weighted Averaging For F…