arXiv research

New approach reduces unconstrained linear bandits to simpler optimization problems.

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

A new optimization algorithm improves convergence in unconstrained problems.

Our paper explains deep neural collapse in multiple layers.

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…

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…

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

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

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

Unconstrained MLIPs outperform constrained ones in accuracy and speed.

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

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

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…

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

New methods solve complex optimization problems in machine learning.

Paper proves fair classification can be done via simple thresholding.

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…

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

Paper analyzes regret bounds for unconstrained online optimization.

Quantum computing improves feature selection in machine learning.

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…

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

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…

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…

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

Cookbook transforms constrained statistical inference into unconstrained problems.

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…

New optimization method for sampling from unknown density measures.

Investigates portfolio optimization with and without gearing constraints.

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

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…

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

Paper tackles bilevel optimization problems using penalty methods.

Structured regularizers enable faster optimization on SPD manifolds with constraints.

We consider the problem of unconstrained online convex optimization (OCO) with sub-exponential noise, a strictly more general problem than the standard OCO. In this setting, the learner receives a subgradient of the loss functions corrupted by sub-exponential noise and strives to achieve optimal regret guarantee, witho…

SurvLIME explains survival models by approximating them with Cox models.

Improved VQE for large DPO problems in finance.

OMWU shows last iterate convergence in convex-concave games.

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

Paper tackles efficient SGD methods for constrained bilevel optimization.

Unconstrained models learn physical symmetries effectively with simple data augmentation.

Efficiently optimizes constrained problems with two-step lookahead BO.

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

New algorithm reduces regret in stochastic bandit convex optimization.

Simulated Bifurcation outperforms quantum machines in community detection.

This work justifies neural collapse under MSE loss and analyzes the optimization landscape.

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

Proposes ConstraintMatch for semi-supervised clustering with unconstrained data.