25 citations · 125 across the 27 of their papers we have counts for
21 papers · 1 filter
Look-Ahead Reasoning on Learning Platforms
Haiqing Zhu, Tijana Zrnic, Celestine Mendler-Dünner
On many learning platforms, the optimization criteria guiding model training reflect the priorities of the designer rather than those of the individuals they affect. Consequently,…
Evaluating language models as risk scores
André F. Cruz, Moritz Hardt, Celestine Mendler-Dünner
Current question-answering benchmarks predominantly focus on accuracy in realizable prediction tasks. Conditioned on a question and answer-key, does the most likely token match the…
Performative Prediction: Past and Future
Moritz Hardt, Celestine Mendler-Dünner
Predictions in the social world generally influence the target of prediction, a phenomenon known as performativity. Self-fulfilling and self-negating predictions are examples of pe…
Performative Power
Moritz Hardt, Meena Jagadeesan, Celestine Mendler-Dünner
We introduce the notion of performative power, which measures the ability of a firm operating an algorithmic system, such as a digital content recommendation platform, to cause cha…
Regret Minimization with Performative Feedback
Meena Jagadeesan, Tijana Zrnic, Celestine Mendler-Dünner
In performative prediction, the deployment of a predictive model triggers a shift in the data distribution. As these shifts are typically unknown ahead of time, the learner needs t…
Alternative Microfoundations for Strategic Classification
Meena Jagadeesan, Celestine Mendler-Dünner, Moritz Hardt
When reasoning about strategic behavior in a machine learning context it is tempting to combine standard microfoundations of rational agents with the statistical decision theory un…
Revisiting Design Choices in Proximal Policy Optimization
Chloe Ching-Yun Hsu, Celestine Mendler-Dünner, Moritz Hardt
Proximal Policy Optimization (PPO) is a popular deep policy gradient algorithm. In standard implementations, PPO regularizes policy updates with clipped probability ratios, and par…
Randomized Block-Diagonal Preconditioning for Parallel Learning
Celestine Mendler-Dünner, Aurelien Lucchi
We study preconditioned gradient-based optimization methods where the preconditioning matrix has block-diagonal form. Such a structural constraint comes with the advantage that the…
Differentially Private Stochastic Coordinate Descent
Georgios Damaskinos, Celestine Mendler-Dünner, Rachid Guerraoui +2
In this paper we tackle the challenge of making the stochastic coordinate descent algorithm differentially private. Compared to the classical gradient descent algorithm where updat…
Stochastic Optimization for Performative Prediction
Celestine Mendler-Dünner, Juan C. Perdomo, Tijana Zrnic +1
In performative prediction, the choice of a model influences the distribution of future data, typically through actions taken based on the model's predictions. We initiate the stud…
Performative Prediction
Juan C. Perdomo, Tijana Zrnic, Celestine Mendler-Dünner +1
When predictions support decisions they may influence the outcome they aim to predict. We call such predictions performative; the prediction influences the target. Performativity i…
SySCD: A System-Aware Parallel Coordinate Descent Algorithm
Nikolas Ioannou, Celestine Mendler-Dünner, Thomas Parnell
In this paper we propose a novel parallel stochastic coordinate descent (SCD) algorithm with convergence guarantees that exhibits strong scalability. We start by studying a state-o…
Breadth-first, Depth-next Training of Random Forests
Andreea Anghel, Nikolas Ioannou, Thomas Parnell +3
In this paper we analyze, evaluate, and improve the performance of training Random Forest (RF) models on modern CPU architectures. An exact, state-of-the-art binary decision tree b…
Addressing Algorithmic Bottlenecks in Elastic Machine Learning with Chicle
Michael Kaufmann, Kornilios Kourtis, Celestine Mendler-Dünner +2
Distributed machine learning training is one of the most common and important workloads running on data centers today, but it is rarely executed alone. Instead, to reduce costs, co…
Sampling Acquisition Functions for Batch Bayesian Optimization
Alessandro De Palma, Celestine Mendler-Dünner, Thomas Parnell +2
We present Acquisition Thompson Sampling (ATS), a novel technique for batch Bayesian Optimization (BO) based on the idea of sampling multiple acquisition functions from a stochasti…
Parallel training of linear models without compromising convergence
Nikolas Ioannou, Celestine Dünner, Kornilios Kourtis +1
In this paper we analyze, evaluate, and improve the performance of training generalized linear models on modern CPUs. We start with a state-of-the-art asynchronous parallel trainin…
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…
Snap ML: A Hierarchical Framework for Machine Learning
Celestine Dünner, Thomas Parnell, Dimitrios Sarigiannis +5
We describe a new software framework for fast training of generalized linear models. The framework, named Snap Machine Learning (Snap ML), combines recent advances in machine learn…
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…
Large-Scale Stochastic Learning using GPUs
Thomas Parnell, Celestine Dünner, Kubilay Atasu +2
In this work we propose an accelerated stochastic learning system for very large-scale applications. Acceleration is achieved by mapping the training algorithm onto massively paral…
Primal-Dual Rates and Certificates
Celestine Dünner, Simone Forte, Martin Takáč +1
We propose an algorithm-independent framework to equip existing optimization methods with primal-dual certificates. Such certificates and corresponding rate of convergence guarante…