arXiv research

Study MNL-Bandit in non-stationary settings with optimal regret bound.

New active learning framework for multiclass classification beyond realizability assumption.

Study minimax regret in bilateral trade with heavy-tailed valuations.

New algorithms adaptively calibrate predictions in non-stationary environments, matching optimal rates.

Algorithm improves reinforcement learning in MDPs with partial order policies.

Study optimal policy regret in partially observable Markov games with adaptive opponents.

We study a class of weakly identifiable location-scale mixture models for which the maximum likelihood estimates based on $n$ i.i.d. samples are known to have lower accuracy than the classical $n^{- \frac{1}{2}}$ error. We investigate whether the Expectation-Maximization (EM) algorithm also converges slowly for these m…

SPARKLE handles high-dimensional covariates for online decision-making.

New algorithm tackles dynamic assortment optimization with knapsack constraints.

Study dynamic assortment and positioning of products with varying display effects.

Lower bounds on eigenspectrum show rich action spaces force polynomial regret in linear bandits.

New algorithm reduces online learning regret in uninformed Markov games.

We propose an efficient ADMM method with guarantees for high-dimensional problems. We provide explicit bounds for the sparse optimization problem and the noisy matrix decomposition problem. For sparse optimization, we establish that the modified ADMM method has an optimal convergence rate of $\mathcal{O}(s\log d/T)$, w…

New algorithm for decentralized matching markets without prior preference rankings.

Study non-rectangular robust MDPs for average-reward, finding optimal policies and transient values.

Study allocates resources to strategic agents while balancing cost and incentives.

Examines algorithmic modeling across three cultures.

Playing repeated matrix games (RMG) while maximizing the cumulative returns is a basic method to evaluate multi-agent learning (MAL) algorithms. Previous work has shown that $UCB$, $M3$, $S$ or $Exp3$ algorithms have good behaviours on average in RMG. Besides, hedging algorithms have been shown to be effective on predi…

Meta-algorithm selection aims to choose the best algorithm selector for a given problem instance.

Proposes CLRS benchmark to evaluate algorithmic reasoning.

Combines multiple bandit algorithms to create a nearly optimal single algorithm.

We propose accelerated randomized coordinate descent algorithms for stochastic optimization and online learning. Our algorithms have significantly less per-iteration complexity than the known accelerated gradient algorithms. The proposed algorithms for online learning have better regret performance than the known rando…

The exchange algorithm is studied for its convergence and asymptotic variance.

Bayesian networks (BN) are used in a big range of applications but they have one issue concerning parameter learning. In real application, training data are always incomplete or some nodes are hidden. To deal with this problem many learning parameter algorithms are suggested foreground EM, Gibbs sampling and RBE algori…

No algorithm outperforms uniform sampling in A/B testing.

Improves algorithm selection for thousands of candidates using dyadic features.

New ELM algorithms reduce computation time and complexity.

This review article surveys data augmentation MCMC algorithms.

Bayesian learning rule unifies and generalizes various machine learning algorithms.

Algorithm design is a laborious process and often requires many iterations of ideation and validation. In this paper, we explore automating algorithm design and present a method to learn an optimization algorithm, which we believe to be the first method that can automatically discover a better algorithm. We approach th…

This review summarizes five Lasso optimization algorithms.

Neural networks mimic algorithms to solve complex problems.

Paper proposes a reinforcement learning framework for efficient hyper-parameter tuning of stochastic optimization algorithms.

Approximate probabilistic inference algorithms are central to many fields. Examples include sequential Monte Carlo inference in robotics, variational inference in machine learning, and Markov chain Monte Carlo inference in statistics. A key problem faced by practitioners is measuring the accuracy of an approximate infe…

In this paper, we propose a convergent parallel best-response algorithm with the exact line search for the nondifferentiable nonconvex sparsity-regularized rank minimization problem. On the one hand, it exhibits a faster convergence than subgradient algorithms and block coordinate descent algorithms. On the other hand,…

New algorithms reduce bilevel optimization complexity to ε^(-1.5).

Researchers analyze how algorithmic and implementation choices affect RL performance.

Study on selecting between base algorithms in stochastic bandit problems.

New bounds derived for KG algorithm's performance in finite time.

Paper proves linear convergence of SCMS algorithm for directional data.

MLE and CVE are equivalent under exponential families, leading to faster and more stable EM algorithms.

We resolve the fundamental problem of online decoding with general $n^{th}$ order ergodic Markov chain models. Specifically, we provide deterministic and randomized algorithms whose performance is close to that of the optimal offline algorithm even when latency is small. Our algorithms admit efficient implementation vi…

New algorithm speeds up learning of graphical models.

The goal of data-driven algorithm design is to obtain high-performing algorithms for specific application domains using machine learning and data. Across many fields in AI, science, and engineering, practitioners will often fix a family of parameterized algorithms and then optimize those parameters to obtain good perfo…

The paper examines how algorithmic classification affects behavior and proposes democratizing stakes to mitigate predatory practices.

Run2Survive uses survival analysis for algorithm selection, outperforming traditional methods.

IRT improves algorithm evaluation across datasets.

New algorithms improve machine learning performance with explicit regret bounds.