arXiv research

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…

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.

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.

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…

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.

Monotonic neural networks have recently been proposed as a way to define invertible transformations. These transformations can be combined into powerful autoregressive flows that have been shown to be universal approximators of continuous probability distributions. Architectures that ensure monotonicity typically enfor…

Quantum computing improves feature selection in machine learning.

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

In this paper, we study two classes of optimal reinsurance models from perspectives of both insurers and reinsurers by minimizing their convex combination where the risk is measured by a distortion risk measure and the premium is given by a distortion premium principle. Firstly, we show that how optimal reinsurance mod…

Neural networks have been used prominently in several machine learning and statistics applications. In general, the underlying optimization of neural networks is non-convex which makes their performance analysis challenging. In this paper, we take a novel approach to this problem by asking whether one can constrain neu…

Properties of steady compressible flow for which geometric constraints have been placed on the potential function are derived, under hypotheses on the flow density and the singular set. Some related unconstrained problems are also considered, including the estimation of a class of fields having nonzero vorticity.

Investigates portfolio optimization with and without gearing constraints.

New samplers minimize KL divergence for constrained and non-Euclidean geometries.

SurvLIME explains survival models by approximating them with Cox models.

Despite significant progress made over the past twenty five years, unconstrained face verification remains a challenging problem. This paper proposes an approach that couples a deep CNN-based approach with a low-dimensional discriminative embedding learned using triplet probability constraints to solve the unconstraine…

In this paper is proposed a new heuristic approach belonging to the field of evolutionary Estimation of Distribution Algorithms (EDAs). EDAs builds a probability model and a set of solutions is sampled from the model which characterizes the distribution of such solutions. The main framework of the proposed method is an…

Study shows 'Ordinal Neural Collapse' in deep OR tasks, revealing simple geometric relationships.