Optimization

Regularized Kernel Kullback-Leibler divergence solves the original KKL’s disjoint support limitation, enabling comparison of any probability distributions with a closed-form solution and efficient gra…

SHORE: a novel two-stage framework efficiently solves sparse & high-dimensional output regression, boosting interpretability and scalability.

Revolutionizing inverse problem solving, this paper introduces diffusion optimal control, a novel framework converting signal recovery into a discrete optimal control problem, surpassing limitations o…

Smoothed online classification can be harder than batch classification when label spaces are unbounded, challenging existing assumptions in machine learning.

DPPs create smaller, more accurate coresets than existing methods, improving machine learning efficiency without sacrificing accuracy.

A novel slack-free spiking neural network efficiently solves the Hypergraph Minimum Vertex Cover problem on neuromorphic hardware, outperforming CPU-based methods in both speed and energy consumption.

SkipPredict optimizes scheduling by prioritizing cheap predictions and using expensive ones only when necessary, achieving cost-effective performance.

SMAG, a novel single-loop stochastic algorithm, achieves state-of-the-art convergence for solving non-smooth non-convex optimization problems involving differences of max-structured weakly convex func…

New shuffling gradient methods achieve state-of-the-art oracle complexity for nonconvex-concave minimax optimization problems, offering improved performance and efficiency.

Sharpness Reduction Interactive Teaching (SRIT) boosts interactive teaching’s performance by integrating SAM’s generalization capabilities, leading to improved model accuracy and generalization.

Researchers developed a recurrent neural circuit model that efficiently transforms sensory signals into neural representations by dynamically adjusting interneuron connectivity and activation function…

SGD surprisingly diminishes network rank, unlike GD, due to a repulsive force between eigenvalues, offering insights into deep learning generalization.

This paper introduces contextual Shtarkov sums, a new complexity measure characterizing minimax regret in sequential probability assignment with contexts, and derives the minimax optimal algorithm, co…

Deep Equilibrium Models (DEQs) outperform standard neural networks, but lack theoretical understanding. This paper provides general separation results showing DEQ’s superior expressivity and character…

This paper introduces a novel, tractable semidefinite program (SDP) relaxation for the Gromov-Wasserstein distance, enabling the computation of globally optimal transportation plans.

New nearly-linear time algorithm achieves high-accuracy semi-random matrix completion, overcoming previous limitations on accuracy and noise tolerance.

Deep learning’s neural scaling laws defy conventional wisdom; this paper uses infinite-dimensional linear regression to theoretically explain this phenomenon, showing that implicit regularization of S…

BICCOS: Scalable neural network verification via branch-and-bound inferred cutting planes.

FOCALBO, a hierarchical Bayesian optimization algorithm using focalized sparse Gaussian processes, efficiently tackles high-dimensional problems with massive datasets, achieving state-of-the-art perfo…

Reconstructing geometry from minimal Euclidean distance samples: A novel algorithm achieves state-of-the-art data efficiency with theoretical guarantees.