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 investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

Semidefinite programming (SDP) is a powerful framework from convex optimization that has striking potential for data science applications. This paper develops a provably correct algorithm for solving large SDP problems by economizing on both the storage an ...

We introduce and analyze an algorithm for the minimization of convex functions that are the sum of differentiable terms and proximable terms composed with linear operators. The method builds upon the recently developed smoothed gap technique. In addition t ...

We present a new algorithm, truncated variance reduction (TruVaR), that treats Bayesian optimization (BO) and level-set estimation (LSE) with Gaussian processes in a unified fashion. The algorithm greedily shrinks a sum of truncated variances within a set ...

We propose a sparse coding approach to address the problem of source-sensor localization and speech reconstruction. This approach relies on designing a dictionary of spatialized signals by projecting the microphone array recordings into the array manifolds ...

Many scientific and engineering applications feature large-scale non-smooth convex minimization problems over convex sets. In this paper, we address an important instance of this broad class where we assume that the non-smooth objective is equipped with a ...

A K*-sparse vector x* ∈ RN produces measurements via linear dimensionality reduction as u = Φx* +n, where Φ ∈ RM×N (M

We introduce the Multiplicative Update Selector and Estimator (MUSE) algorithm for sparse approximation in under-determined linear regression problems. Given ƒ = Φα* + μ, the MUSE provably and efficiently finds a k-sparse vector α̂ such that ∥Φα̂ − ƒ∥∞ ≤ ∥ ...

Recovery of sparse signals from linear, dimensionality reducing measurements broadly fall under two well-known formulations, named the synthesis and the analysis a ́ la Elad et al. Recently, Chandrasekaran et al. introduced a new algorithmic sparse recover ...

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

In this paper, we extend the generalized approximate message passing (G-AMP) approach, originally proposed for high-dimensional generalized-linear regression in the context of compressive sensing, to the generalized-bilinear case, which enables its applica ...

Metasurfaces based on resonant subwavelength photonic structures enable novel ways of wavefront control and light focusing, underpinning a new generation of flat-optics devices. Recently emerged all-dielectric asymmetric metasurfaces, composed of arrays of ...

We propose a conditional gradient framework for a composite convex minimization template with broad applications. Our approach combines the notions of smoothing and homotopy under the CGM framework, and provably achieves the optimal O(1/sqrt(k)) convergenc ...

We propose a stochastic optimization method for the minimization of the sum of three convex functions, one of which has Lipschitz continuous gradient as well as restricted strong convexity. Our approach is most suitable in the setting where it is computati ...

Since Polyak's pioneering work, heavy ball (HB) momentum has been widely studied in minimization. However, its role in min-max games remains largely unexplored. As a key component of practical min-max algorithms like Adam, this gap limits their effectivene ...

This paper provides a theoretical study of deep neural function approximation in reinforcement learning (RL) with the ϵ-greedy exploration under the online setting. This problem setting is motivated by the successful deep Q-networks (DQN) framework that fa ...

We consider the problem of finding a K-sparse approximation of a signal, such that the support of the approximation is the union of sets from a given collection, a.k.a. group structure. This problem subsumes the one of finding K-sparse tree approximations. ...

Interest in deep probabilistic graphical models has increased in recent years, due to their state-of-the-art perfor- mance on many machine learning applications. Such models are typically trained with the stochastic gradient method, which can take a signif ...

We study the classical problem of maximizing a monotone submodular function subject to a cardinality constraint k, with two additional twists: (i) elements arrive in a streaming fashion and (ii) m items from the algorithm’s memory might be removed after th ...

This paper presents a theoretical analysis of linear interpolation as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss lan ...

Volkan Cevher

Chattez avec Graph Search

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Scalable Semidefinite Programming

Smoothing technique for nonsmooth composite minimization with linear operator

Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation

Binary Sparse Coding of Convolutive Mixtures for Sound Localization and Separation via Spatialization

An inexact proximal path-following algorithm for constrained convex minimization

Online performance guarantees for sparse recovery

Compressive sensing meets game theory

Equivalence of synthesis and atomic formulations of sparse recovery

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Bilinear Generalized Approximate Message Passing—Part I: Derivation

Ultrasensitive hyperspectral imaging and biodetection enabled by dielectric metasurfaces

A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming

Stochastic Three-Composite Convex Minimization

Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games

Understanding Deep Neural Function Approximation in Reinforcement Learning via ϵ-Greedy Exploration

Sparse Group Covers and Greedy Tree Approximations

Stochastic Spectral Descent for Discrete Graphical Models

Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach

Stable Nonconvex-Nonconcave Training via Linear Interpolation