arXiv research

Paper proposes DG-ETC for online submodular maximization with stochastic bandit feedback.

Solves VaR-constrained portfolio optimization in markets with stochastic volatility.

An optimal algorithm maximizes submodular functions online with no-1/2 regret.

Study optimal portfolio management with periodic evaluations in stochastic models, considering convex constraints.

The natural gradient of ELBO vanishes in unconstrained optimization, simplifying learning.

We investigate the ergodic problem of growth-rate maximization under a class of risk constraints in the context of incomplete, Itô-process models of financial markets with random ergodic coefficients. Including {\em value-at-risk} (VaR), {\em tail-value-at-risk} (TVaR), and {\em limited expected loss} (LEL), these cons…

Study uses RL to optimize investment with financial constraints, showing exploration benefits.

In Bipartite Correlation Clustering (BCC) we are given a complete bipartite graph $G$ with `+' and `-' edges, and we seek a vertex clustering that maximizes the number of agreements: the number of all `+' edges within clusters plus all `-' edges cut across clusters. BCC is known to be NP-hard. We present a novel approx…

The study connects fairness constraints with optimal transport to derive new insights in classification.

The study clarifies fairness guarantees from unconstrained machine learning, showing group calibration is often satisfied but at the cost of other criteria.

We study Spectral Measures of Risk from the perspective of portfolio optimization. We derive exact results which extend to general Spectral Measures M_phi the Pflug--Rockafellar--Uryasev methodology for the minimization of alpha--Expected Shortfall. The minimization problem of a spectral measure is shown to be equivale…

Unconstrained MLIPs outperform constrained ones in accuracy and speed.

Our paper explains deep neural collapse in multiple layers.

Pairwise learning usually refers to a learning task which involves a loss function depending on pairs of examples, among which most notable ones include ranking, metric learning and AUC maximization. In this paper, we study an online algorithm for pairwise learning with a least-square loss function in an unconstrained …

Non-linear systems of differential equations have attracted the interest in fields like system biology, ecology or biochemistry, due to their flexibility and their ability to describe dynamical systems. Despite the importance of such models in many branches of science they have not been the focus of systematic statisti…

New approach reduces unconstrained linear bandits to simpler optimization problems.

Study how regularization and optimization affect margin in deep models.

Develops parameter-free online mirror descent for optimal dynamic regret.

We propose an expectation-maximization-like(EMlike) method to train Boltzmann machine with unconstrained connectivity. It adopts Monte Carlo approximation in the E-step, and replaces the intractable likelihood objective with efficiently computed objectives or directly approximates the gradient of likelihood objective i…

A new optimization algorithm improves convergence in unconstrained problems.

Unconstrained models learn physical symmetries effectively with simple data augmentation.

Proposes ConstraintMatch for semi-supervised clustering with unconstrained data.

Agents cooperate to make decisions in multi-armed bandits over a graph.

The paper explores solving inverse problems for ODEs with and without constraints.

Study shows equivalence of four risk constraints in non-concave optimization problems.

BOSS optimizes string inputs using string kernels and genetic algorithms.

This paper extends neural collapse to class-imbalanced datasets using an unconstrained ReLU feature model.

New algorithms reduce online learning regret by tracking gradient variation.

Lower-dimensional video discriminators improve GAN performance.

A new L-BFGS method tackles large-scale optimization with fewer evaluations.

GOPO optimizes large models in Hilbert space, avoiding Kullback-Leibler's curvature.

New algorithm minimizes cumulative loss in dynamic linear bandits without prior knowledge of comparator switches.

This thesis explores how submodularity aids in optimizing non-convex functions and validating algorithms.

New algorithm solves utility maximization with deep learning for constrained problems.

New algorithms reduce regret in unconstrained online learning with unknown parameters.

Optimizes stock portfolios with a constraint on correlation to reduce risk.

New method uses neural networks to solve PDEs without grid discretization.

In most machine learning applications, classification accuracy is not the primary metric of interest. Binary classifiers which face class imbalance are often evaluated by the $F_β$ score, area under the precision-recall curve, Precision at K, and more. The maximization of many of these metrics can be expressed as a con…

We propose an online convex optimization algorithm (RescaledExp) that achieves optimal regret in the unconstrained setting without prior knowledge of any bounds on the loss functions. We prove a lower bound showing an exponential separation between the regret of existing algorithms that require a known bound on the los…

VoxCeleb 2019 challenge assesses speaker recognition in uncontrolled settings.

Paper proposes a QUBO formulation that reduces binary variables in Bayesian network learning.

VAV method optimizes learning rate for faster, stable SGD convergence.

We consider a variant of online convex optimization in which both the instances (input vectors) and the comparator (weight vector) are unconstrained. We exploit a natural scale invariance symmetry in our unconstrained setting: the predictions of the optimal comparator are invariant under any linear transformation of th…

Cookbook transforms constrained statistical inference into unconstrained problems.

Paper tackles robust MDPs with sample complexity guarantees.

DP-GD achieves dimension-independent convergence for unconstrained private GLMs.

TopoFisher learns topological summaries by maximizing Fisher information, improving parameter efficiency and inference quality.

We consider the \mnk{classical} problem of a controller activating (or sampling) sequentially from a finite number of $N \geq 2$ populations, specified by unknown distributions. Over some time horizon, at each time $n = 1, 2, \ldots$, the controller wishes to select a population to sample, with the goal of sampling fro…