
Regret minimization in stochastic nonconvex learning via a proximalgradient approach
Motivated by applications in machine learning and operations research, w...
read it

Random extrapolation for primaldual coordinate descent
We introduce a randomly extrapolated primaldual coordinate descent meth...
read it

Conditional gradient methods for stochastically constrained convex minimization
We propose two novel conditional gradientbased methods for solving stru...
read it

Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch
We study the inverse reinforcement learning (IRL) problem under the tran...
read it

DoubleLoop Unadjusted Langevin Algorithm
A wellknown firstorder method for sampling from logconcave probabilit...
read it

Efficient Proximal Mapping of the 1pathnorm of Shallow Networks
We demonstrate two new important properties of the 1pathnorm of shallo...
read it

Interactionlimited Inverse Reinforcement Learning
This paper proposes an inverse reinforcement learning (IRL) framework to...
read it

Environment Shaping in Reinforcement Learning using State Abstraction
One of the central challenges faced by a reinforcement learning (RL) age...
read it

On the Almost Sure Convergence of Stochastic Gradient Descent in NonConvex Problems
This paper analyzes the trajectories of stochastic gradient descent (SGD...
read it

The limits of minmax optimization algorithms: convergence to spurious noncritical sets
Compared to minimization problems, the minmax landscape in machine lear...
read it

Convergence of adaptive algorithms for weakly convex constrained optimization
We analyze the adaptive first order algorithm AMSGrad, for solving a con...
read it

Lipschitz constant estimation of Neural Networks via sparse polynomial optimization
We introduce LiPopt, a polynomial optimization framework for computing i...
read it

A new regret analysis for Adamtype algorithms
In this paper, we focus on a theorypractice gap for Adam and its varian...
read it

A Newton FrankWolfe Method for Constrained SelfConcordant Minimization
We demonstrate how to scalably solve a class of constrained selfconcord...
read it

Robust Reinforcement Learning via Adversarial training with Langevin Dynamics
We introduce a sampling perspective to tackle the challenging task of tr...
read it

Optimization for Reinforcement Learning: From Single Agent to Cooperative Agents
This article reviews recent advances in multiagent reinforcement learni...
read it

UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization
We propose a novel adaptive, accelerated algorithm for the stochastic co...
read it

Nearly Minimal OverParametrization of Shallow Neural Networks
A recent line of work has shown that an overparametrized neural network ...
read it

Fast and Provable ADMM for Learning with Generative Priors
In this work, we propose a (linearized) Alternating Direction Methodof...
read it

Interactive Teaching Algorithms for Inverse Reinforcement Learning
We study the problem of inverse reinforcement learning (IRL) with the ad...
read it

On Certifying Nonuniform Bound against Adversarial Attacks
This work studies the robustness certification problem of neural network...
read it

Streaming LowRank Matrix Approximation with an Application to Scientific Simulation
This paper argues that randomized linear sketching is a natural tool for...
read it

An OptimalStorage Approach to Semidefinite Programming using Approximate Complementarity
This paper develops a new storageoptimal algorithm that provably solves...
read it

Stochastic Conditional Gradient Method for Composite Convex Minimization
In this paper, we propose the first practical algorithm to minimize stoc...
read it

An Introductory Guide to Fano's Inequality with Applications in Statistical Estimation
Information theory plays an indispensable role in the development of alg...
read it

Efficient learning of smooth probability functions from Bernoulli tests with guarantees
We study the fundamental problem of learning an unknown, smooth probabil...
read it

Iterative Classroom Teaching
We consider the machine teaching problem in a classroomlike setting whe...
read it

Kernel Conjugate Gradient Methods with Random Projections
We propose and study kernel conjugate gradient methods (KCGM) with rando...
read it

Adversarially Robust Optimization with Gaussian Processes
In this paper, we consider the problem of Gaussian process (GP) optimiza...
read it

Finding Mixed Nash Equilibria of Generative Adversarial Networks
We reconsider the training objective of Generative Adversarial Networks ...
read it

Online Adaptive Methods, Universality and Acceleration
We present a novel method for convex unconstrained optimization that, wi...
read it

LearningBased Compressive MRI
In the area of magnetic resonance imaging (MRI), an extensive range of n...
read it

Optimal Rates of Sketchedregularized Algorithms for LeastSquares Regression over Hilbert Spaces
We investigate regularized algorithms combining with projection for leas...
read it

Mirrored Langevin Dynamics
We generalize the Langevin Dynamics through the mirror descent framework...
read it

Dimensionfree Information Concentration via ExpConcavity
Information concentration of probability measures have important implica...
read it

Robust Maximization of NonSubmodular Objectives
We study the problem of maximizing a monotone set function subject to a ...
read it

HighDimensional Bayesian Optimization via Additive Models with Overlapping Groups
Bayesian optimization (BO) is a popular technique for sequential blackb...
read it

Let's be honest: An optimal noregret framework for zerosum games
We revisit the problem of solving twoplayer zerosum games in the decen...
read it

Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and SpectralRegularization Algorithms
We study generalization properties of distributed algorithms in the sett...
read it

Optimal Rates for Spectralregularized Algorithms with LeastSquares Regression over Hilbert Spaces
In this paper, we study regression problems over a separable Hilbert spa...
read it

Smooth PrimalDual Coordinate Descent Algorithms for Nonsmooth Convex Optimization
We propose a new randomized coordinate descent method for a convex optim...
read it

Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach
We study the classical problem of maximizing a monotone submodular funct...
read it

Phase Transitions in the Pooled Data Problem
In this paper, we study the pooled data problem of identifying the label...
read it

Combinatorial Penalties: Which structures are preserved by convex relaxations?
We consider the homogeneous and the nonhomogeneous convex relaxations f...
read it

FixedRank Approximation of a PositiveSemidefinite Matrix from Streaming Data
Several important applications, such as streaming PCA and semidefinite p...
read it

Robust Submodular Maximization: A NonUniform Partitioning Approach
We study the problem of maximizing a monotone submodular function subjec...
read it

Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization
In this paper, we consider the problem of sequentially optimizing a blac...
read it

Faster Coordinate Descent via Adaptive Importance Sampling
Coordinate descent methods employ random partial updates of decision var...
read it

Sketchy Decisions: Convex LowRank Matrix Optimization with Optimal Storage
This paper concerns a fundamental class of convex matrix optimization pr...
read it

Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and LevelSet Estimation
We present a new algorithm, truncated variance reduction (TruVaR), that ...
read it
Volkan Cevher
is this you? claim profile
Associate Professor at Ecole Polytechnique Federale de Lausanne