Publications by Volkan Cevher | EPFL Graph Search

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 consider the group testing problem, in which one seeks to identify a subset of defective items within a larger set of items based on a number of tests. We characterize the information-theoretic performance limits in the presence of list decoding, in whi ...

We propose a Bayesian approach where the signal structure can be represented by a mixture model with a submodular prior. We consider an observation model that leads to Lipschitz functions. Due to its combinatorial nature, computing the maximum a posteriori ...

Neural Architecture Search (NAS) has fostered the automatic discovery of stateof- the-art neural architectures. Despite the progress achieved with NAS, so far there is little attention to theoretical guarantees on NAS. In this work, we study the generaliza ...

This article reviews recent advances in convex optimization algorithms for Big Data, which aim to reduce the computational, storage, and communications bottlenecks. We provide an overview of this emerging field, describe contemporary approximation techniqu ...

In this paper, we revisit an efficient algorithm for noisy group testing in which each item is decoded separately (Malyutov and Mateev, 1980), and develop novel performance guarantees via an information-theoretic framework for general noise models. For the ...

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. ...

This paper describes scalable convex optimization methods for phase retrieval. The main characteristics of these methods are the cheap per-iteration complexity and the low-memory footprint. With a variant of the original PhaseLift formulation, we first ill ...

Deep Neural Networks (DNNs) have obtained impressive performance across tasks, however they still remain as black boxes, e.g., hard to theoretically analyze. At the same time, Polynomial Networks (PNs) have emerged as an alternative method with a promising ...

This paper considers a fundamental class of convex matrix optimization problems with low-rank solutions. We show it is possible to solve these problem using far less memory than the natural size of the decision variable when the problem data has a concise ...

We propose a novel adaptive, accelerated algorithm for the stochastic constrained convex optimization setting. Our method, which is inspired by the Mirror-Prox method, \emph{simultaneously} achieves the optimal rates for smooth/non-smooth problems with eit ...

This paper introduces the SOAR framework for imitation learning. SOAR is an algorithmic template that learns a policy from expert demonstrations with a primal dual style algorithm that alternates cost and policy updates. Within the policy updates, the SOAR ...

In this paper, we consider the problem of maximizing a monotone submodular function subject to a cardinality constraint, with two added twists: The computation is distributed across a number of machines, and we require the solution to be robust against adv ...

We study the sparsity of spectro-temporal representation of speech in reverberant acoustic conditions. This study motivates the use of structured sparsity models for efﬁcient speech recovery. We formulate the underdetermined convolutive speech separation i ...

A well-known first-order method for sampling from log-concave probability distributions is the Unadjusted Langevin Algorithm (ULA). This work proposes a new annealing step-size schedule for ULA, which allows to prove new convergence guarantees for sampling ...

This work reports an 8-lane single-ended RX featuring compact and low power far-end crosstalk (FEXT) cancellation circuits. The RX data-path consists of a cross continuous-time linear equalizer (XCTLE) to remove FEXT by nearest aggressors within the channe ...

Volkan Cevher

Chat with Graph Search

How little does non-exact recovery help in group testing?

MAP Estimation for Bayesian Mixture Models with Submodular Priors

Generalization Properties of NAS under Activation and Skip Connection Search

Convex Optimization for Big Data

Near-Optimal Noisy Group Testing via Separate Decoding of Items

Alternation makes the adversary weaker in two-player games

Scalable Convex Methods for Phase Retrieval

Machine Learning From Distributed, Streaming Data [From the Guest Editors]

Regularization of polynomial networks for image recognition

Sketchy Decisions: Convex Low-Rank Matrix Optimization with Optimal Storage

UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization

IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic

What can online reinforcement learning with function approximation benefitfrom general coverage conditions

A Distributed Algorithm for Partitioned Robust Submodular Maximization

Multi-party Speech Recovery Exploiting Structured Sparsity Models

Double-Loop Unadjusted Langevin Algorithm

A 5.9mW/Gb/s 7Gb/s/pin 8-Lane Single-Ended RX with Crosstalk Cancellation Scheme using a XCTLE and 56-tap XDFE in 32nm SOI CMOS