arXiv research

Study on $H$-consistency bounds for machine learning surrogates.

Study improves $H$-consistency bounds for regression analysis.

Enhanced $H$-consistency bounds derived under relaxed conditions.

Enhanced consistency bounds derived for classification under a new noise condition.

Study of loss functions for learning to defer, proving consistency.

Unified surrogate loss framework for multi-label learning with strong consistency guarantees.

The paper bounds eigenvalues and integrals of eigenfunctions on hyperbolic manifolds.

This paper is devoted to regret lower bounds in the classical model of stochastic multi-armed bandit. A well-known result of Lai and Robbins, which has then been extended by Burnetas and Katehakis, has established the presence of a logarithmic bound for all consistent policies. We relax the notion of consistence, and e…

The paper derives upper bounds on eigenvalues of Laplace-Beltrami operator on hyperbolic surfaces.

Study on top-$k$ classification with new loss functions and algorithms.

MaxMatch improves SSL with worst-case consistency for better generalization.

Study shows $k$-NN regressor consistency in complex survey designs.

Develops a framework for consistent pricing of interest rate derivatives.

This paper improves multi-label ranking by reweighting univariate losses, enhancing consistency and performance.

Reduces bounded loss learning to binary classification.

Study tightens bounds for interpolating noisy data using minimum l1-norm.

Novel Orlicz regrets consistently bound environmental variable statistics.

Study shows how discrete graph curvature relates to manifold curvature.

New method improves consistency in preference learning for neural networks.

We study revenue optimization learning algorithms for repeated posted-price auctions where a seller interacts with a single strategic buyer that holds a fixed private valuation for a good and seeks to maximize his cumulative discounted surplus. For this setting, first, we propose a novel algorithm that never decreases …

This article studies the achievable guarantees on the error rates of certain learning algorithms, with particular focus on refining logarithmic factors. Many of the results are based on a general technique for obtaining bounds on the error rates of sample-consistent classifiers with monotonic error regions, in the real…

We establish the first nonasymptotic error bounds for Kaplan-Meier-based nearest neighbor and kernel survival probability estimators where feature vectors reside in metric spaces. Our bounds imply rates of strong consistency for these nonparametric estimators and, up to a log factor, match an existing lower bound for c…

Paper establishes a universal growth rate for smooth surrogate losses in classification.

Bootstrap bounds on Einstein manifolds using semidefinite programming.

AUC (area under ROC curve) is an important evaluation criterion, which has been popularly used in many learning tasks such as class-imbalance learning, cost-sensitive learning, learning to rank, etc. Many learning approaches try to optimize AUC, while owing to the non-convexity and discontinuousness of AUC, almost all …

This paper tackles deferral learning with multiple experts, providing strong theoretical guarantees.

Any bounding compact smooth manifold bounds a compact manifold with a spine consisting of transversely intersecting codimension one submanifolds. This paper provides details for a picture proof given in previous papers with S. Akbulut.

In distributed ML applications, shared parameters are usually replicated among computing nodes to minimize network overhead. Therefore, proper consistency model must be carefully chosen to ensure algorithm's correctness and provide high throughput. Existing consistency models used in general-purpose databases and moder…

Novel bounds improve TD learning consistency in RL.

We study time-consistency questions for processes of monetary risk measures that depend on bounded discrete-time processes describing the evolution of financial values. The time horizon can be finite or infinite. We call a process of monetary risk measures time-consistent if it assigns to a process of financial values …

The paper develops estimators for variance in graph structures using fused lasso.

Improves risk and variability measures continuity and consistency.

We study the off-policy evaluation problem---estimating the value of a target policy using data collected by another policy---under the contextual bandit model. We consider the general (agnostic) setting without access to a consistent model of rewards and establish a minimax lower bound on the mean squared error (MSE).…

Upper bound found for Steklov eigenvalue of a surface of revolution.

Uniform convergence of interpolators proven for Gaussian data.

We study collapsed manifolds with Ricci bounded covering geometry i.e., Ricci curvature is bounded below and the Riemannian universal cover is non-collapsed or consists of uniform Reifenberg points. Via Ricci flows' techniques, we partially extend the nilpotent structural results of Cheeger-Fukaya-Gromov, on collapsed …

Sharp bounds on ATE with unmeasured confounders, valid even when misspecified.

We consider the problem of finding a consistent upper price bound for exotic options whose payoff depends on the stock price at two different predetermined time points (e.g. Asian option), given a finite number of observed call prices for these maturities. A model-free approach is used, only taking into account that th…

Paper bounds convergence rate of adversarial surrogate risk.

Theoretical analysis of cross-entropy loss functions and their robustness.

Paper improves Bayesian regret bounds for Thompson Sampling in reinforcement learning.

WPCA improves subspace recovery robustness to outliers.

The paper proposes methods for predicting missing values in mixed data matrices.

We study consistency properties of machine learning methods based on minimizing convex surrogates. We extend the recent framework of Osokin et al. (2017) for the quantitative analysis of consistency properties to the case of inconsistent surrogates. Our key technical contribution consists in a new lower bound on the ca…

A new lower bound on the complexity of a 3-manifold is given using the Z2-Thurston norm. This bound is shown to be sharp, and the minimal triangulations realising it are characterised using normal surfaces consisting entirely of quadrilateral discs.

Dynamic submodular maximization with consistency constraints.

Study of estimation errors in surrogate loss minimizers, providing stronger guarantees than existing methods.

Convex clustering can only learn convex clusters, with significant gaps between clusters.