417 citations · 859 across the 22 of their papers we have counts for
22 papers
IGDA: Interactive Graph Discovery through Large Language Model Agents
Alex Havrilla, David Alvarez-Melis, Nicolo Fusi
Large language models () have emerged as a powerful method for discovery. Instead of utilizing numerical data, LLMs utilize associated variable $\textit{semantic met…
Adapting Language Models via Token Translation
Zhili Feng, Tanya Marwah, Nicolo Fusi +2
Modern large language models use a fixed tokenizer to effectively compress text drawn from a source domain. However, applying the same tokenizer to a new target domain often leads…
Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains
Junhong Shen, Neil Tenenholtz, James Brian Hall +2
Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding and generating natural language. However, their capabilities wane in highly specialized domai…
Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine
Harsha Nori, Yin Tat Lee, Sheng Zhang +15
Generalist foundation models such as GPT-4 have displayed surprising capabilities in a wide variety of domains and tasks. Yet, there is a prevalent assumption that they cannot matc…
Budget-Constrained Bounds for Mini-Batch Estimation of Optimal Transport
David Alvarez-Melis, Nicolò Fusi, Lester Mackey +1
Optimal Transport (OT) is a fundamental tool for comparing probability distributions, but its exact computation remains prohibitive for large datasets. In this work, we introduce n…
Interpretable Distribution Shift Detection using Optimal Transport
Neha Hulkund, Nicolo Fusi, Jennifer Wortman Vaughan +1
We propose a method to identify and characterize distribution shifts in classification datasets based on optimal transport. It allows the user to identify the extent to which each…
Bayesian Optimization Over Iterative Learners with Structured Responses: A Budget-aware Planning Approach
Syrine Belakaria, Janardhan Rao Doppa, Nicolo Fusi +1
The rising growth of deep neural networks (DNNs) and datasets in size motivates the need for efficient solutions for simultaneous model selection and training. Many methods for hyp…
On Hard Episodes in Meta-Learning
Samyadeep Basu, Amr Sharaf, Nicolo Fusi +1
Existing meta-learners primarily focus on improving the average task accuracy across multiple episodes. Different episodes, however, may vary in hardness and quality leading to a w…
Rapid Model Architecture Adaption for Meta-Learning
Yiren Zhao, Xitong Gao, Ilia Shumailov +2
Network Architecture Search (NAS) methods have recently gathered much attention. They design networks with better performance and use a much shorter search time compared to traditi…
LANA: Latency Aware Network Acceleration
Pavlo Molchanov, Jimmy Hall, Hongxu Yin +3
We introduce latency-aware network acceleration (LANA) - an approach that builds on neural architecture search techniques and teacher-student distillation to accelerate neural netw…
Initialization and Regularization of Factorized Neural Layers
Mikhail Khodak, Neil Tenenholtz, Lester Mackey +1
Factorized layers--operations parameterized by products of two or more matrices--occur in a variety of deep learning contexts, including compressed model training, certain types of…
Model-specific Data Subsampling with Influence Functions
Anant Raj, Cameron Musco, Lester Mackey +1
Model selection requires repeatedly evaluating models on a given dataset and measuring their relative performances. In modern applications of machine learning, the models being con…
Dataset Dynamics via Gradient Flows in Probability Space
David Alvarez-Melis, Nicolò Fusi
Various machine learning tasks, from generative modeling to domain adaptation, revolve around the concept of dataset transformation and manipulation. While various methods exist fo…
Weighted Meta-Learning
Diana Cai, Rishit Sheth, Lester Mackey +1
Meta-learning leverages related source tasks to learn an initialization that can be quickly fine-tuned to a target task with limited labeled examples. However, many popular meta-le…
Geometric Dataset Distances via Optimal Transport
David Alvarez-Melis, Nicolò Fusi
The notion of task similarity is at the core of various machine learning paradigms, such as domain adaptation and meta-learning. Current methods to quantify it are often heuristic,…
Feature Gradients: Scalable Feature Selection via Discrete Relaxation
Rishit Sheth, Nicolo Fusi
In this paper we introduce Feature Gradients, a gradient-based search algorithm for feature selection. Our approach extends a recent result on the estimation of learnability in the…
Probabilistic Neural Architecture Search
Francesco Paolo Casale, Jonathan Gordon, Nicolo Fusi
In neural architecture search (NAS), the space of neural network architectures is automatically explored to maximize predictive accuracy for a given task. Despite the success of re…
Teacher-Student Compression with Generative Adversarial Networks
Ruishan Liu, Nicolo Fusi, Lester Mackey
More accurate machine learning models often demand more computation and memory at test time, making them difficult to deploy on CPU- or memory-constrained devices. Teacher-student…
Gaussian Process Prior Variational Autoencoders
Francesco Paolo Casale, Adrian V Dalca, Luca Saglietti +2
Variational autoencoders (VAE) are a powerful and widely-used class of models to learn complex data distributions in an unsupervised fashion. One important limitation of VAEs is th…
Probabilistic Matrix Factorization for Automated Machine Learning
Nicolo Fusi, Rishit Sheth, Huseyn Melih Elibol
In order to achieve state-of-the-art performance, modern machine learning techniques require careful data pre-processing and hyperparameter tuning. Moreover, given the ever increas…
Genetic Analysis of Transformed Phenotypes
Nicolo Fusi, Christoph Lippert, Neil D. Lawrence +1
Linear mixed models (LMMs) are a powerful and established tool for studying genotype-phenotype relationships. A limiting assumption of LMMs is that the residuals are Gaussian distr…
Gaussian Processes for Big Data
James Hensman, Nicolo Fusi, Neil D. Lawrence
We introduce stochastic variational inference for Gaussian process models. This enables the application of Gaussian process (GP) models to data sets containing millions of data poi…