arXiv research

Improved bounds for Monte Carlo Rademacher Averages using self-bounding functions.

Optimistic bounds for multi-output learning using self-bounding Lipschitz condition.

Gradient descent converges with arbitrary stepsize for separable data under Fenchel-Young losses.

Prediction suffix trees (PST) provide an effective tool for sequence modelling and prediction. Current prediction techniques for PSTs rely on exact matching between the suffix of the current sequence and the previously observed sequence. We present a provably correct algorithm for learning a PST with approximate suffix…

New algorithms minimize PAC-Bayesian C-Bound for majority voting, leading to scalable and accurate predictors.

Paper shows TD learning without projection converges robustly.

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

We explore the family of methods "PAC-Bayes with Backprop" (PBB) to train probabilistic neural networks by minimizing PAC-Bayes bounds. We present two training objectives, one derived from a previously known PAC-Bayes bound, and a second one derived from a novel PAC-Bayes bound. Both training objectives are evaluated o…

New PAC-Bayesian bounds for multi-view learning using Rényi divergence.

New risk measures control subgroup imbalances, improving PAC-Bayesian bounds.

Perceptron is a classic online algorithm for learning a classification function. In this paper, we provide a novel extension of the perceptron algorithm to the learning to rank problem in information retrieval. We consider popular listwise performance measures such as Normalized Discounted Cumulative Gain (NDCG) and Av…

Algorithm learns both stochastic and adversarial MDPs with best-of-both-worlds guarantees.

PAC-Bayesian framework for fairness in stochastic and deterministic classifiers.

Improved regret bounds for Tsallis-INF in adversarial bandits and corruptions.

We derive an algorithm that achieves the optimal (within constants) pseudo-regret in both adversarial and stochastic multi-armed bandits without prior knowledge of the regime and time horizon. The algorithm is based on online mirror descent (OMD) with Tsallis entropy regularization with power $α=1/2$ and reduced-varian…

TD(0) with Polyak-Ruppert averaging achieves robust and fast convergence rates

Optimizes pruning masks for neural networks using probabilistic fine-tuning and PAC-Bayes bounds.

Study online learning in MDPs with aggregate bandit feedback, achieving low regret in both stochastic and adversarial settings.

We consider the problem of online adaptive control of the linear quadratic regulator, where the true system parameters are unknown. We prove new upper and lower bounds demonstrating that the optimal regret scales as $\widetildeΘ({\sqrt{d_{\mathbf{u}}^2 d_{\mathbf{x}} T}})$, where $T$ is the number of time steps, $d_{\m…

This paper is concerned with offline reinforcement learning (RL), which learns using pre-collected data without further exploration. Effective offline RL would be able to accommodate distribution shift and limited data coverage. However, prior algorithms or analyses either suffer from suboptimal sample complexities or …

New approach tackles resource constraints in bandit problems with weakly adaptive algorithms.

Gradient descent on shallow neural networks achieves near-optimal generalization error.

Develops PAC-Bayesian framework for physics-informed machine learning.

Develops a strategy to minimize loss in both stochastic and adversarial environments for linear contextual bandits.

New neural network models for complex functional data analysis.

Distance function to a finite set is a topological Morse function.

Introduces new weighted floating functions and affine surface areas.

Develops methods for selecting and estimating smooth functional coefficients in high-dimensional multivariate functional data.

Neural networks can approximate functionals on RKHS with error bounds.

FFBO optimizes functions as inputs and outputs, improving on existing BO methods.

Chirped sinosoids and interferometric phase plots are functions that are not periodic, but are the composition of a smooth function and a periodic function. These functions functions factor into a pair of maps: from their domain to a circle, and from a circle to their codomain. One can easily imagine replacing the circ…

The Fridman function is bounded by the injectivity radius for certain hyperbolic manifolds.

Optimally estimates a functional using nuisance function tuning and sample splitting.

The paper proves isoparametric functions on Finsler space forms under specific conditions.

Paper introduces a nonparametric functional graphical model for random functions.

Robustifies elicitable functionals to handle small distribution misspecifications.

The paper characterizes strong Hamel functions using symmetries and proves their preservation properties.

Study biharmonic functions on vector bundles with spherical symmetry.

Two new methods improve forecasting of functional time series data.

This paper introduces the concept of functional current as a mathematical framework to represent and treat functional shapes, i.e. sub-manifold supported signals. It is motivated by the growing occurrence, in medical imaging and computational anatomy, of what can be described as geometrico-functional data, that is a da…

Study stabilizers of smooth functions on surfaces, focusing on Morse-Bott functions.

The paper connects convex functions to p-subharmonic functions and proves their equivalence.

A new deep neural network tackles nonlinear functional regression with improved dimensionality reduction.

New model for network analysis using functional data.

The study finds a special type of smooth function on connected sums of manifolds.

Function trees simplify complex ML models for better understanding.

We study functions whose truncations are convex or quasiconvex.

NeuTSFlow models continuous functions behind time series forecasting.