arXiv research

New algorithms improve exploration in unbounded reward settings.

We introduce a new stochastic smoothing perspective to study adversarial contextual bandit problems. We propose a general algorithm template that represents random perturbation based algorithms and identify several perturbation distributions that lead to strong regret bounds. Using the idea of smoothness, we provide an…

Improved regret bounds for bandits with fixed expert advice using information theory.

New algorithm improves cache management with delayed feedback and decaying costs.

Meta-algorithm optimizes nonstochastic bandits with infinitely many experts.

New algorithm bounds regret in mediator feedback bandit problems.

A new algorithm reduces inference error in adaptive contextual bandits.

We provide the first algorithm for online bandit linear optimization whose regret after T rounds is of order sqrt{Td ln N} on any finite class X of N actions in d dimensions, and of order d*sqrt{T} (up to log factors) when X is infinite. These bounds are not improvable in general. The basic idea utilizes tools from con…

New algorithm reduces sleeping bandits' regret to O(sqrt(T)).

Improves reward bounds for prediction with expert advice using abstention.

Most contextual bandit algorithms minimize regret against the best fixed policy, a questionable benchmark for non-stationary environments that are ubiquitous in applications. In this work, we develop several efficient contextual bandit algorithms for non-stationary environments by equipping existing methods for i.i.d. …

Near-optimal per-action regret bounds for sleeping bandits are derived.

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.

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.

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,…

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…

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

The inverse-free extreme learning machine (ELM) algorithm proposed in [4] was based on an inverse-free algorithm to compute the regularized pseudo-inverse, which was deduced from an inverse-free recursive algorithm to update the inverse of a Hermitian matrix. Before that recursive algorithm was applied in [4], its impr…

Researchers analyze how algorithmic and implementation choices affect RL performance.

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

Paper proves linear convergence of SCMS algorithm for directional data.

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…

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

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.

The Kaczmarz algorithm is popular for iteratively solving an overdetermined system of linear equations. The traditional Kaczmarz algorithm can approximate the solution in few sweeps through the equations but a randomized version of the Kaczmarz algorithm was shown to converge exponentially and independent of number of …

The book explores alternatives to worst-case analysis for algorithm performance.

Paper proposes an unsupervised feature selection algorithm with stability guarantees.

Recently manifold learning algorithm for dimensionality reduction attracts more and more interests, and various linear and nonlinear, global and local algorithms are proposed. The key step of manifold learning algorithm is the neighboring region selection. However, so far for the references we know, few of which propos…

New hybrid RL algorithm outperforms model-free and model-based methods.

Algorithm selection (AS) deals with selecting an algorithm from a fixed set of candidate algorithms most suitable for a specific instance of an algorithmic problem, e.g., choosing solvers for SAT problems. Benchmark suites for AS usually comprise candidate sets consisting of at most tens of algorithms, whereas in combi…