arXiv research

New constraints on space and adaptivity in bandits force more batches and memory use.

The paper optimizes risk-sensitive RL with CVaR, achieving near-minimax-optimal results.

Optimizes treatment allocation using covariates for better outcomes.

Improved privacy in RL with near-optimal regret bounds.

SA algorithms control dynamic regret in non-stationary settings with strong convexity or exp-concavity.

Tr-LinUCB reduces regret in stochastic linear bandits by truncating exploration.

UCB algorithms improve on bandit problems with precise regret analysis and adaptive inference.

Paper quantizes heavy-tailed data for near optimal estimation rates.

Bayesian KANs achieve near-minimax posterior contraction rates in anisotropic Besov spaces.

Bayesian PINNs learn elliptic PDEs with near-minimax posterior contraction rate.

OptiNet achieves near-minimax error rates with compression in Euclidean space.

This work establishes near-minimax optimal guarantees for ODE-based samplers under mild assumptions.

Estimating signals with linear recurrence relations under Gaussian noise is nearly as hard as sparse signals.

We analyze the Kozachenko--Leonenko (KL) nearest neighbor estimator for the differential entropy. We obtain the first uniform upper bound on its performance over Hölder balls on a torus without assuming any conditions on how close the density could be from zero. Accompanying a new minimax lower bound over the Hölder ba…

New RL algorithm minimizes distributional learning error.

Study minimax-optimal rates for offline decision-making with function approximation.

This paper describes a recursive estimation procedure for multivariate binary densities (probability distributions of vectors of Bernoulli random variables) using orthogonal expansions. For $d$ covariates, there are $2^d$ basis coefficients to estimate, which renders conventional approaches computationally prohibitive …

New statistical framework for coresets in density estimation.

Variational inference is becoming more and more popular for approximating intractable posterior distributions in Bayesian statistics and machine learning. Meanwhile, a few recent works have provided theoretical justification and new insights on deep neural networks for estimating smooth functions in usual settings such…

New algorithm reduces TV-denoising to adaptive online learning.

New method for efficient matrix completion with nonignorable missing data.

Spike-and-Slab Deep Learning (SS-DL) is a fully Bayesian alternative to Dropout for improving generalizability of deep ReLU networks. This new type of regularization enables provable recovery of smooth input-output maps with unknown levels of smoothness. Indeed, we show that the posterior distribution concentrates at t…

Paper proposes algorithms to minimize both dynamic and adaptive regret simultaneously.

The paper analyzes the sliding regret of stochastic bandit algorithms.

This paper analyzes regret bounds for Gaussian process Thompson sampling.

New theory for BNNs with Gaussian priors achieves optimal posterior concentration rates.

New BNN model proves optimal posterior concentration and enables practical inference.

The notion of \emph{policy regret} in online learning is a well defined? performance measure for the common scenario of adaptive adversaries, which more traditional quantities such as external regret do not take into account. We revisit the notion of policy regret and first show that there are online learning settings …

A single policy suffices for near-optimal parallel exploration in RL.

Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the standard definition of regret becomes inadequate if the adversary is allowed to a…

Paper tackles offline SSP with value iteration for policy evaluation and learning.

Balances the regret of different algorithms in bandit and RL problems.

Data-driven model selection reduces regret in sequential decisions.

Optimistic Hedge achieves optimal regret bounds in two-player zero-sum games.

We consider an online learning process to forecast a sequence of outcomes for nonconvex models. A typical measure to evaluate online learning algorithms is regret but such standard definition of regret is intractable for nonconvex models even in offline settings. Hence, gradient based definition of regrets are common f…

Optimal switching regret for all segmentations in online convex optimisation.

New method robustifies topological data analysis against outliers.

New approach for distributed online optimization of non-convex losses with sublinear regret.

New algorithm SELECT minimizes satisficing regret in bandits.

The paper tackles efficient online learning by achieving minimal regret with respect to the best expert.

Regret minimization is a powerful tool for solving large-scale problems; it was recently used in breakthrough results for large-scale extensive-form game solving. This was achieved by composing simplex regret minimizers into an overall regret-minimization framework for extensive-form game strategy spaces. In this paper…

We study the Thompson sampling algorithm in an adversarial setting, specifically, for adversarial bit prediction. We characterize the bit sequences with the smallest and largest expected regret. Among sequences of length $T$ with $k < \frac{T}{2}$ zeros, the sequences of largest regret consist of alternating zeros and …

This paper considers the stability of online learning algorithms and its implications for learnability (bounded regret). We introduce a novel quantity called {\em forward regret} that intuitively measures how good an online learning algorithm is if it is allowed a one-step look-ahead into the future. We show that given…

Paper introduces a new $G^\star$ regret measure for online convex optimization with smooth losses.

Bandit algorithms struggle with consistent performance and robustness.

This paper investigates the problem of active learning for binary label prediction on a graph. We introduce a simple and label-efficient algorithm called S2 for this task. At each step, S2 selects the vertex to be labeled based on the structure of the graph and all previously gathered labels. Specifically, S2 queries f…

Paper improves worst-case regret bounds for RLSVI in reinforcement learning.

Paper solves no-swap regret minimization for combinatorial bandits with polylogarithmic dependence on N.