Publications de Volkan Cevher | EPFL Graph Search

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

This paper proposes a smoothing technique for nonsmooth convex minimization using self-concordant barriers. To illustrate the main ideas, we compare our technique and the proximity smoothing approach (Nesterov2005) via the classical gradient method on both ...

The self-concordant-like property of a smooth convex function is a new analytical structure that generalizes the self-concordant notion. While a wide variety of important applications feature the self- concordant-like property, this concept has heretofore ...

We introduce algorithms based on natural actorcritic and analyze their sample complexity for solving two player zero-sum Markov games in the tabular case. Our results improve the best-known sample complexities of policy gradient/actorcritic methods for con ...

The group testing problem consists of determining a sparse subset of a set of items that are ``defective'' based on a set of possibly noisy tests, and arises in areas such as medical testing, fault detection, communication protocols, pattern matching, and ...

While the class of Polynomial Nets demonstrates comparable performance to neural networks (NN), it currently has neither theoretical generalization characterization nor robustness guarantees. To this end, we derive new complexity bounds for the set of Coup ...

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robus ...

We consider the sequential Bayesian optimization problem with bandit feedback, adopting a formulation that allows for the reward function to vary with time. We model the reward function using a Gaussian process whose evolution obeys a simple Markov model. ...

The support recovery problem consists of deter- mining a sparse subset of a set of variables that is relevant in generating a set of observations, and arises in a diverse range of settings such as group testing, compressive sensing, and subset selection in ...

The present invention concerns a method of sampling a test signal. The method comprises: acquiring (21) training signals sampled at a plurality of sampling locations; running (23) an optimization procedure for determining an index set of n indices, represe ...

We propose a new self-adaptive and double-loop smoothing algorithm to solve composite, nonsmooth, and constrained convex optimization problems. Our algorithm is based on Nesterov’s smoothing technique via general Bregman distance functions. It self-adaptiv ...

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...

We propose and analyze an online algorithm for reconstructing a sequence of signals from a limited number of linear measurements. The signals are assumed sparse, with unknown support, and evolve over time according to a generic nonlinear dynamical model. O ...

In this work, we study optimization methods that leverage the linear minimization oracle (lmo) over a norm-ball. We propose a new stochastic family of algorithms that uses the lmo to adapt to the geometry of the problem and, perhaps surprisingly, show that ...

We examine the problem of regret minimization when the learner is involved in a continuous game with other optimizing agents: in this case, if all players follow a no-regret algorithm, it is possible to achieve significantly lower regret relative to fully ...

We propose a new proximal, path-following framework for a class of---possibly non-smooth---constrained convex problems. We consider settings where the non-smooth part is endowed with a proximity operator, and the constraint set is equipped with a self-conc ...

We initiate the study of the classical Submodular Cover (SC) problem in the data streaming model which we refer to as the Streaming Submodular Cover (SSC). We show that any single pass streaming algorithm using sublinear memory in the size of the stream wi ...

We develop universal gradient methods for Stochastic Convex Optimization (SCO). Our algorithms automatically adapt not only to the oracle's noise but also to the Hölder smoothness of the objective function without a priori knowledge of the particular setti ...

We introduce LiPopt, a polynomial optimization framework for computing increasingly tighter upper bounds on the Lipschitz constant of neural networks. The underlying optimization problems boil down to either linear (LP) or semidefinite (SDP) programming. W ...

We investigate regularized algorithms combining with projection for least-squares regression problem over a Hilbert space, covering nonparametric regression over a reproducing kernel Hilbert space. We prove convergence results with respect to variants of n ...

Volkan Cevher

Chattez avec Graph Search

Barrier Smoothing for Nonsmooth Convex Minimization

Composite convex minimization involving self-concordant-like cost functions

A Natural Actor-Critic Framework for Zero-Sum Markov Games

Phase Transitions in Group Testing

Controlling the Complexity and Lipschitz Constant improves Polynomial Nets

Robust NAS under adversarial training: benchmark, theory, and beyond

Time-Varying Gaussian Process Bandit Optimization

Limits on Support Recovery with Probabilistic Models: An Information-Theoretic Framework

Learning-based subsampling

An adaptive primal-dual framework for nonsmooth convex minimization

Efficient local linearity regularization to overcome catastrophic overfitting

Adaptive-Rate Reconstruction of Time-Varying Signals with Application in Compressive Foreground Extraction

Introduction to the Issue on Signal Processing for Big Data

Training Deep Learning Models with Norm-Constrained LMOs

No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation

A single-phase, proximal path-following framework

An Efficient Streaming Algorithm for the Submodular Cover Problem

Universal Gradient Methods for Stochastic Convex Optimization

Lipschitz constant estimation for Neural Networks via sparse polynomial optimization

Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces