Stochastic Learning Under Random Reshuffling With Constant Step-Sizes

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

We develop a principled approach to end-to-end learning in stochastic optimization. First, we show that the standard end-to-end learning algorithm admits a Bayesian interpretation and trains a posterior Bayes action map. Building on the insights of this an ...

As large, data-driven artificial intelligence models become ubiquitous, guaranteeing high data quality is imperative for constructing models. Crowdsourcing, community sensing, and data filtering have long been the standard approaches to guaranteeing or imp ...

Motivated by alternating game-play in two-player games, we study an altenating variant of the Online Linear Optimization (OLO). In alternating OLO, a learner at each round t ∈[n] selects a vector xt and then an adversary selects a cost-vector ct ∈[−1,1]n. ...

The paper presents ICAP (interactive, constructive, active and passive) as the theoretical framework to understand the role of informal learning spaces as an active learning tool when students have informal meetings to work on projects. Students in our En ...

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by early-stopped unconstrain ...

This work proposes a decentralized architecture, where individual agents aim at solving a classification problem while observing streaming features of different dimensions and arising from possibly different distributions. In the context of social learning ...

In the field of choice modeling, the availability of ever-larger datasets has the potential to significantly expand our understanding of human behavior, but this prospect is limited by the poor scalability of discrete choice models (DCMs): as sample sizes ...

Within the context of contemporary machine learning problems, efficiency of optimization process depends on the properties of the model and the nature of the data available, which poses a significant problem as the complexity of either increases ad infinit ...

This paper considers the problem of resilient distributed optimization and stochastic learning in a server-based architecture. The system comprises a server and multiple agents, where each agent has its own local cost function. The agents collaborate with ...

Non-convex constrained optimization problems have become a powerful framework for modeling a wide range of machine learning problems, with applications in k-means clustering, large- scale semidefinite programs (SDPs), and various other tasks. As the perfor ...

The monumental progress in the development of machine learning models has led to a plethora of applications with transformative effects in engineering and science. This has also turned the attention of the research community towards the pursuit of construc ...

The variational approach is a cornerstone of computational physics, considering both conventional and quantum computing computational platforms. The variational quantum eigensolver algorithm aims to prepare the ground state of a Hamiltonian exploiting para ...

Handwriting is an important skill in children development as well as in education that take years to be mastered. While keyboards and similar technological devices increasingly become more popular, new tools and engaging approaches are also required to kee ...

Model-free Reinforcement Learning (RL) generally suffers from poor sample complexity, mostly due to the need to exhaustively explore the state-action space to find well-performing policies. On the other hand, we postulate that expert knowledge of the syste ...

In this thesis, we explore techniques for addressing the communication bottleneck in data-parallel distributed training of deep learning models. We investigate algorithms that either reduce the size of the messages that are exchanged between workers, or th ...

Blood pressure (BP) is a crucial indicator of cardiovascular health. Hypertension is a common life-threatening condition and a key factor of cardiovascular diseases (CVDs). Identifying abnormal BP fluctuations can allow for early detection and management o ...

Stochastic Learning Under Random Reshuffling With Constant Step-Sizes

Chat with Graph Search

End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

Extensions of Peer Prediction Incentive Mechanisms

Alternation makes the adversary weaker in two-player games

Work in progress: Imagining / Designing informal spaces for learning

The statistical complexity of early-stopped mirror descent

Learning From Heterogeneous Data Based on Social Interactions Over Graphs

Stochastic adaptive resampling for the estimation of discrete choice models

Universal and adaptive methods for robust stochastic optimization

Impact of Redundancy on Resilience in Distributed Optimization and Learning

Augmented Lagrangian Methods for Provable and Scalable Machine Learning

Probabilistic methods for neural combinatorial optimization

Phenomenological theory of variational quantum ground-state preparation

The iReCheck project: using tablets and robots for personalised handwriting practice

Computationally Efficient Reinforcement Learning: Targeted Exploration leveraging Simple Rules

Communication-efficient distributed training of machine learning models

Data-driven approaches for non-invasive cuffless blood pressure monitoring