arXiv research

Proposes a flexible tournament design combining knockout and round-robin.

Improved elimination strategies for adaptive bandit identification reduce sample complexity and computational burden.

Classification may not be reliable for several reasons: noise in the data, insufficient input information, overlapping distributions and sharp definition of classes. Faced with several possibilities neural network may in such cases still be useful if instead of a classification elimination of improbable classes is done…

New algorithm eliminates arms to minimize regret in complex bandit problems.

Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant. In such cases, it is sometimes easier to learn which actions not to take. In this work, we propose the Action-Elimination…

We introduce Neural Choice by Elimination, a new framework that integrates deep neural networks into probabilistic sequential choice models for learning to rank. Given a set of items to chose from, the elimination strategy starts with the whole item set and iteratively eliminates the least worthy item in the remaining …

Aims to eliminate domain bias in authentication without domain labels.

We simplify Khovanov homology for torus braids using Gaussian elimination.

Logic approach finds real singularities in differential equations.

A wide class of machine learning algorithms can be reduced to variable elimination on factor graphs. While factor graphs provide a unifying notation for these algorithms, they do not provide a compact way to express repeated structure when compared to plate diagrams for directed graphical models. To exploit efficient t…

We develop an approach for feature elimination in statistical learning with kernel machines, based on recursive elimination of features.We present theoretical properties of this method and show that it is uniformly consistent in finding the correct feature space under certain generalized assumptions.We present four cas…

In this paper, we theoretically prove that adding one special neuron per output unit eliminates all suboptimal local minima of any deep neural network, for multi-class classification, binary classification, and regression with an arbitrary loss function, under practical assumptions. At every local minimum of any deep n…

Two new feature selection algorithms improve on RFE.

In this paper, we consider the problem of online learning of Markov decision processes (MDPs) with very large state spaces. Under the assumptions of realizable function approximation and low Bellman ranks, we develop an online learning algorithm that learns the optimal value function while at the same time achieving ve…

PoWER-BERT speeds up BERT inference by eliminating redundant word-vectors.

GPE algorithm optimizes nonparametric contextual bandits with efficient regret bounds.

We propose a computationally efficient wrapper feature selection method - called Autoencoder and Model Based Elimination of features using Relevance and Redundancy scores (AMBER) - that uses a single ranker model along with autoencoders to perform greedy backward elimination of features. The ranker model is used to pri…

Probabilistic graphical models offer a powerful framework to account for the dependence structure between variables, which is represented as a graph. However, the dependence between variables may render inference tasks intractable. In this paper we review techniques exploiting the graph structure for exact inference, b…

We present a provably optimal differentially private algorithm for the stochastic multi-arm bandit problem, as opposed to the private analogue of the UCB-algorithm [Mishra and Thakurta, 2015; Tossou and Dimitrakakis, 2016] which doesn't meet the recently discovered lower-bound of $Ω\left(\frac{K\log(T)}ε \right)$ [Shar…

A new algorithm optimizes local objectives in federated learning with heterogeneous clients.

Paper eliminates warm-up phase for PO in linear MDPs, achieving optimal regret.

Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor sample efficiency. To mitigate this issue, a number of variance-reduction approaches have been prop…

Robust algorithm optimizes corrupted Gaussian process bandits.

Classifies SL(n) covariant matrix-valued valuations on Lp-spaces.

The paper discusses the impossibility of eliminating surplus intersections in Lagrangian submanifolds.

Balances and eliminates base algorithms in bandits and RL to bound total regret.

Discontinuous Finite Element Methods (DFEM) have been widely used for solving $S_n$ radiation transport problems in participative and non-participative media. In the DFEM $S_n$ methodology, the transport equation is discretized into a set of algebraic equations that have to be solved for each spatial cell and angular d…

New method eliminates domain size restrictions for X-ray transform inversion.

New method simplifies optimization landscapes by transforming saddle points.

This paper clarifies vine copula structures using graph and matrix representations.

An algorithm learns from multiple models to match an oracle's risk.

This paper has been withdrawn. Its new version has been published.

SDD improves DD for estimating treatment effects by adjusting for confounding.

New algorithms identify Pareto optimal sets in multi-objective bandit problems.

New study shows non-adaptive trials can be outperformed by adaptive designs in treatment selection.

Extensive neural networks eliminate the need for SABR pricing formulas.

In this paper, we first give a new simple proof to the elimination theorem of definite fold by homotopy for generic smooth maps of manifolds of dimension strictly greater than $2$ into the $2$--sphere or into the real projective plane. Our new proof has the advantage that it is not only constructive, but is also algori…

We consider the best-arm identification problem in multi-armed bandits, which focuses purely on exploration. A player is given a fixed budget to explore a finite set of arms, and the rewards of each arm are drawn independently from a fixed, unknown distribution. The player aims to identify the arm with the largest expe…

Unknot recognition is one of the fundamental questions in low dimensional topology. In this work, we show that this problem can be encoded as a validity problem in the existential fragment of the first-order theory of real closed fields. This encoding is derived using a well-known result on SU(2) representations of kno…

We study the general structure of formal perturbative solutions to the Hamiltonian perturbations of spatially one-dimensional systems of hyperbolic PDEs. Under certain genericity assumptions it is proved that any bihamiltonian perturbation can be eliminated in all orders of the perturbative expansion by a change of coo…

The paper tackles best arm identification in contaminated bandits with optimal error guarantees and sample complexity.

Margin maximization in the hard-margin sense, proposed as feature elimination criterion by the MFE-LO method, is combined here with data radius utilization to further aim to lower generalization error, as several published bounds and bound-related formulations pertaining to lowering misclassification risk (or error) pe…

Music genre classification is an essential tool for music information retrieval systems and it has been finding critical applications in various media platforms. Two important problems of the automatic music genre classification are feature extraction and classifier design. This paper investigates inter-genre similarit…

Improves early stopping in deep networks by adjusting stepsizes.

Polarization measurements done using Imaging Polarimeters such as the Robotic Polarimeter are very sensitive to the presence of artefacts in images. Artefacts can range from internal reflections in a telescope to satellite trails that could contaminate an area of interest in the image. With the advent of wide-field pol…

Computing the partition function $Z$ of a discrete graphical model is a fundamental inference challenge. Since this is computationally intractable, variational approximations are often used in practice. Recently, so-called gauge transformations were used to improve variational lower bounds on $Z$. In this paper, we pro…

Study quantile multi-armed bandits for identifying the best arm with a specified quantile level.

DRSSS method reduces model training costs by eliminating unsafe samples.