arXiv research

Paper presents adaptive minimax risk classifiers for multidimensional concept drift.

The paper analyzes the efficiency of unlearning methods and establishes bounds for minimax computation times.

Paper explores statistical and computational limits of estimating low-rank Gaussian mixtures.

We investigate the use of Minimax distances to extract in a nonparametric way the features that capture the unknown underlying patterns and structures in the data. We develop a general-purpose and computationally efficient framework to employ Minimax distances with many machine learning methods that perform on numerica…

Improved MMD test for two-sample testing with random Fourier features.

Optimizes variational inference for dynamic network models.

In recent years, sparse principal component analysis has emerged as an extremely popular dimension reduction technique for high-dimensional data. The theoretical challenge, in the simplest case, is to estimate the leading eigenvector of a population covariance matrix under the assumption that this eigenvector is sparse…

New algorithm achieves optimal regret in average reward MDPs without prior bias information.

TiAda adapts adaptive gradient methods for nonconvex minimax optimization.

New evidence shows computational barriers in graphon estimation using low-degree polynomials.

Paper tackles sparse recovery with shuffled labels, establishing statistical and computational limits.

New method solves complex constrained optimization problems.

Adversarial meta-learning computes Gamma-minimax estimators for vague prior knowledge.

We extend the traditional worst-case, minimax analysis of stochastic convex optimization by introducing a localized form of minimax complexity for individual functions. Our main result gives function-specific lower and upper bounds on the number of stochastic subgradient evaluations needed to optimize either the functi…

Paper proposes efficient methods for clustering and signal recovery in high-dimensional data with block structures.

In this paper we give sufficient conditions guaranteeing the validity of the well-known minimax theorem for the lower Snell envelope with respect to a family of absolutely continuous probability measures. Such minimax results play an important role in the characterisation of arbitrage-free prices of American contingent…

New algorithm ranks players from partial comparisons with optimal rate.

Study non-stationary distributions, proving risk bounds for density estimation.

Optimally estimate distances on surfaces using reconstructed meshes.

MOTS improves Thompson sampling to match minimax bounds for bandit problems.

In this work, we study the problem of aggregating a finite number of predictors for nonstationary sub-linear processes. We provide oracle inequalities relying essentially on three ingredients: (1) a uniform bound of the $\ell^1$ norm of the time varying sub-linear coefficients, (2) a Lipschitz assumption on the predict…

Cheap permutation tests speed up distribution testing without sacrificing accuracy.

A federated minimax framework for heterogeneous clients.

New algorithm computes optimal transport barycenter efficiently.

We establish optimal convergence rates for a decomposition-based scalable approach to kernel ridge regression. The method is simple to describe: it randomly partitions a dataset of size N into m subsets of equal size, computes an independent kernel ridge regression estimator for each subset, then averages the local sol…

Study minimax optimal RL in factored MDPs with bonus exploration.

Estimates isotonic functions under unknown permutations, achieving optimal statistical and computational efficiency.

Flexible framework for modeling predictive distributions of time series

E$^4$ algorithm optimizes batched linear bandits with minimal regret and batches.

New algorithm solves nonconvex-convex minimax problems efficiently.

New algorithms solve nonconvex-nonconcave minimax optimization problems.

New method tackles nonconvex-nonconcave problems with local KL condition.

Optimal algorithm for linear bandits on ellipsoids with minimax regret bound.

New algorithm for solving minimax problems over distributions converges to Nash equilibrium.

The paper develops a new algorithm for constructing minimax estimators using online learning techniques.

The paper identifies network bottlenecks using minimax paths in stochastic networks.

We introduce a new method for sparse principal component analysis, based on the aggregation of eigenvector information from carefully-selected axis-aligned random projections of the sample covariance matrix. Unlike most alternative approaches, our algorithm is non-iterative, so is not vulnerable to a bad choice of init…

Improved analysis shows Maillard sampling achieves optimal regret bounds.

Kernel ridge regression (KRR) is a standard method for performing non-parametric regression over reproducing kernel Hilbert spaces. Given $n$ samples, the time and space complexity of computing the KRR estimate scale as $\mathcal{O}(n^3)$ and $\mathcal{O}(n^2)$ respectively, and so is prohibitive in many cases. We prop…

This paper tackles convex-submodular minimax problems in mixed continuous-discrete domains.

Paper improves risk bounds for nonconvex-strongly-concave minimax problems.

We perform a finite sample analysis of the detection levels for sparse principal components of a high-dimensional covariance matrix. Our minimax optimal test is based on a sparse eigenvalue statistic. Alas, computing this test is known to be NP-complete in general, and we describe a computationally efficient alternativ…

We consider the problem of link prediction, based on partial observation of a large network, and on side information associated to its vertices. The generative model is formulated as a matrix logistic regression. The performance of the model is analysed in a high-dimensional regime under a structural assumption. The mi…

We consider the problem of two-player zero-sum games. This problem is formulated as a min-max Markov game in the literature. The solution of this game, which is the min-max payoff, starting from a given state is called the min-max value of the state. In this work, we compute the solution of the two-player zero-sum game…

Standard Transformers approximate Hölder functions and achieve optimal nonparametric regression rate.

New model optimizes feature alignment, improving statistical and computational efficiency.

We provide a unified treatment of a broad class of noisy structure recovery problems, known as structured normal means problems. In this setting, the goal is to identify, from a finite collection of Gaussian distributions with different means, the distribution that produced some observed data. Recent work has studied s…

New method for efficient matrix completion with nonignorable missing data.