arXiv research

This paper evaluates conformal prediction for aerial image classification in challenging environments.

Study on consistency of ML methods for moving objects in non-stationary environments.

IRM fails to capture natural invariances on simple problems.

New algorithm ensures consistent results in constrained MAB problems.

Parametric insurance offers better risk-sharing in high-risk settings than traditional indemnity insurance.

Reinforcement learning and planning methods require an objective or reward function that encodes the desired behavior. Yet, in practice, there is a wide range of scenarios where an objective is difficult to provide programmatically, such as tasks with visual observations involving unknown object positions or deformable…

Unconstrained MLIPs outperform constrained ones in accuracy and speed.

Our paper explains deep neural collapse in multiple layers.

New approach reduces unconstrained linear bandits to simpler optimization problems.

We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we characterize when unconstrained learning on its own implies group calibration, that is, the outcome variable is conditionally independent of group membership given the score. We show that under r…

This article addresses the modeling of reverberant recording environments in the context of under-determined convolutive blind source separation. We model the contribution of each source to all mixture channels in the time-frequency domain as a zero-mean Gaussian random variable whose covariance encodes the spatial cha…

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

A new optimization algorithm improves convergence in unconstrained problems.

Unconstrained models learn physical symmetries effectively with simple data augmentation.

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

Proposes ConstraintMatch for semi-supervised clustering with unconstrained data.

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.

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

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

Domain shift is unavoidable in real-world applications of object detection. For example, in self-driving cars, the target domain consists of unconstrained road environments which cannot all possibly be observed in training data. Similarly, in surveillance applications sufficiently representative training data may be la…

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…

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…

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

Cookbook transforms constrained statistical inference into unconstrained problems.

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

Yau's Affine Normal Descent optimizes smooth unconstrained problems with geometrically adapted directions.

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

OOM-RL uses financial market losses to align AI agents in autonomous systems.

Paper tackles constrained bandit problems with a new learning framework.

In recent years, a myriad of advanced results have been reported in the community of imitation learning, ranging from parametric to non-parametric, probabilistic to non-probabilistic and Bayesian to frequentist approaches. Meanwhile, ample applications (e.g., grasping tasks and human-robot collaborations) further show …

Adam converges with high probability under unconstrained non-convex smooth stochastic optimizations.

Paper analyzes regret bounds for unconstrained online optimization.

A drawdown constraint forces the current wealth to remain above a given function of its maximum to date. We consider the portfolio optimisation problem of maximising the long-term growth rate of the expected utility of wealth subject to a drawdown constraint, as in the original setup of Grossman and Zhou (1993). We wor…

New methods solve complex optimization problems in machine learning.

New sparse Gaussian process method tackles unconstrained regression problems.

This article presents a new methodology called deep Theory of Functional Connections (TFC) that estimates the solutions of partial differential equations (PDEs) by combining neural networks with TFC. TFC is used to transform PDEs with boundary conditions into unconstrained optimization problems by embedding the boundar…

The paper studies knot densities under various constraints and degenerations.

We consider minimizing a nonconvex, smooth function $f$ on a Riemannian manifold $\mathcal{M}$. We show that a perturbed version of Riemannian gradient descent algorithm converges to a second-order stationary point (and hence is able to escape saddle points on the manifold). The rate of convergence depends as $1/ε^2$ o…

This paper extends neural collapse to imbalanced data under cross-entropy loss.

Proposes an evolutionary approach to fitting acyclic VAR models.

Paper proves fair classification can be done via simple thresholding.

We study optimization methods for solving the maximum likelihood formulation of independent component analysis (ICA). We consider both the the problem constrained to white signals and the unconstrained problem. The Hessian of the objective function is costly to compute, which renders Newton's method impractical for lar…

New algorithm improves online learning with reduced discretization.

Develops methods for estimating constrained function-valued parameters in infinite-dimensional models.

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

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