arXiv research

New method speeds up diffusion models inference to sub-linear time.

Bayesian optimisation algorithm for unknown search spaces with sub-linear regret.

Deep Retrieval learns a retrievable structure for efficient large-scale recommendations.

We provide a novel -- and to the best of our knowledge, the first -- algorithm for high dimensional sparse regression with constant fraction of corruptions in explanatory and/or response variables. Our algorithm recovers the true sparse parameters with sub-linear sample complexity, in the presence of a constant fractio…

Study finds exact limits for sparse regression with fewer observations than usual.

Kernel $ε$-Greedy optimizes multi-armed bandits with covariates for sub-linear regret.

In this paper, we study a class of online optimization problems with long-term budget constraints where the objective functions are not necessarily concave (nor convex) but they instead satisfy the Diminishing Returns (DR) property. Specifically, a sequence of monotone DR-submodular objective functions $\{f_t(x)\}_{t=1…

Optimal Liouville theorem for minimal disks in any codimension.

Paper tackles LDP bandits learning with improved results and sub-linear regret.

First robust bandit algorithm for contextual bandits with sub-linear regret.

In this paper, we introduce Ballooning Multi-Armed Bandits (BL-MAB), a novel extension of the classical stochastic MAB model. In the BL-MAB model, the set of available arms grows (or balloons) over time. In contrast to the classical MAB setting where the regret is computed with respect to the best arm overall, the regr…

New algorithm tackles adversarial corruption in Lipschitz bandits with sub-linear regret.

LNUCB-TA improves MAB performance by dynamically adjusting exploration rates and recognizing spatiotemporal patterns.

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…

We revisit the inductive matrix completion problem that aims to recover a rank-$r$ matrix with ambient dimension $d$ given $n$ features as the side prior information. The goal is to make use of the known $n$ features to reduce sample and computational complexities. We present and analyze a new gradient-based non-convex…

This paper addresses robust CBs for linear SEMs with model fluctuations.

In $\mathcal{X}$-armed bandit problem an agent sequentially interacts with environment which yields a reward based on the vector input the agent provides. The agent's goal is to maximise the sum of these rewards across some number of time steps. The problem and its variations have been a subject of numerous studies, su…

In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems. By leveraging modern techniques in distributed controller synthesis and structured linear inverse problems as applied to system identification, we show that near-optimal distributed con…

New algorithms reduce slate bandit regret for large slates, outperforming existing methods.

Optimal ReLU networks can memorize any separable set of points with a small number of parameters.

In this paper, we consider the problem of preserving privacy in the online learning setting. We study the problem in the online convex programming (OCP) framework---a popular online learning setting with several interesting theoretical and practical implications---while using differential privacy as the formal privacy …

New algorithms for planning with adversarial changes in costs.

Paper tackles domain adaptation for contextual bandits with sub-linear regret.

Study of deep Stable neural networks with various activation functions.

Efficient algorithms for $k$-means clustering frequently converge to suboptimal partitions, and given a partition, it is difficult to detect $k$-means optimality. In this paper, we develop an a posteriori certifier of approximate optimality for $k$-means clustering. The certifier is a sub-linear Monte Carlo algorithm b…

COBRA addresses strategic behavior in online platforms by ensuring truthful reporting without monetary incentives.

In some reinforcement learning problems an agent may be provided with a set of input policies, perhaps learned from prior experience or provided by advisors. We present a reinforcement learning with policy advice (RLPA) algorithm which leverages this input set and learns to use the best policy in the set for the reinfo…

In recent years there has been an increasing interest in learning Bayesian networks from data. One of the most effective methods for learning such networks is based on the minimum description length (MDL) principle. Previous work has shown that this learning procedure is asymptotically successful: with probability one,…

Proposes a transductive matrix completion method with calibration for multi-task learning.

Safe Gaussian Process Bandit Optimization with sub-linear regret bounds.

Proposes SPFB method for optimizing partition functions in stochastic learning.

Neural algorithms optimize arm selection with human preference feedback for complex reward functions.

We explore a novel setting of the Multi-Armed Bandit (MAB) problem inspired from real world applications which we call bandits with "stochastic delayed composite anonymous feedback (SDCAF)". In SDCAF, the rewards on pulling arms are stochastic with respect to time but spread over a fixed number of time steps in the fut…

New algorithm reduces risk in online games with limited feedback.

Upper bounds on ribbonlength of various knots, showing linear and sub-linear behavior.

This paper proposes asal, a new GAN based active learning method that generates high entropy samples. Instead of directly annotating the synthetic samples, ASAL searches similar samples from the pool and includes them for training. Hence, the quality of new samples is high and annotations are reliable. To the best of o…

Multi-armed bandits are a quintessential machine learning problem requiring the balancing of exploration and exploitation. While there has been progress in developing algorithms with strong theoretical guarantees, there has been less focus on practical near-optimal finite-time performance. In this paper, we propose an …

A new algorithm improves stochastic linear bandit performance using residual bootstrap.

New algorithms for fair item allocation with limited copies.

New algorithms achieve uniform-PAC guarantees for RL with bounded eluder dimension.

The paper tackles minimax optimality in continuum contextual bandits with Hölder continuity.

G-framework is presented by Peng [41] for measure risk under uncertainty. In this paper, we define fractional G-Brownian motion (fGBm). Fractional G-Brownian motion is a centered G-Gaussian process with zero mean and stationary increments in the sense of sub-linearity with Hurst index $H\in (0,1)$. This process has sta…

New NTK bounds show deep networks with minimum over-parameterization can still memorize and optimize.

New BO method optimizes functions efficiently even with unknown hyperparameters.

Two models predict similar high-frequency price dynamics but differ in low-frequency impact strength.

SURF simplifies distribution estimation with simple, robust, and fast algorithms.

Paper tackles online DR-submodular maximization with stochastic constraints.

Being able to reason in an environment with a large number of discrete actions is essential to bringing reinforcement learning to a larger class of problems. Recommender systems, industrial plants and language models are only some of the many real-world tasks involving large numbers of discrete actions for which curren…