Optimization

Unlocking latent community structures from multiple correlated networks is now possible with greater precision, as this research pinpoints the information-theoretic threshold for exact recovery, even …

HardCore: Fast generation of hard, realistic UNSAT problems for improved SAT solver runtime prediction.

GTG, a novel conditional generative modeling approach, leverages diffusion models to generate high-scoring design trajectories for offline model-based optimization, outperforming existing methods on b…

This paper presents a novel optimistic mirror descent algorithm achieving optimal gradient-variation regret under generalized smoothness, applicable across convex, strongly convex functions, and fast-…

Gradient-free methods conquer nonconvex nonsmooth stochastic compositional optimization, providing non-asymptotic convergence rates and improved efficiency for real-world applications.

Novel gradient-based algorithms achieve O(√T) regret and O(T3/4) constraint violation for online DR-submodular maximization with stochastic long-term constraints.

This paper provides a novel optimization framework for guided diffusion models, proving Õ(1/K) convergence for concave objective functions and demonstrating structure-preserving guidance.

A globally Q-linearly converging Gauss-Newton method (AGN) is introduced for overparameterized non-convex low-rank matrix sensing, significantly improving convergence compared to existing gradient des…

Researchers achieve globally convergent variational inference by minimizing the expected forward KL divergence, overcoming the limitations of traditional methods.

Large-scale Transformer training’s global convergence is proven using weight decay regularization and a refined mean-field analysis, bridging theory and practice.

GLinSAT: A novel neural network layer efficiently solves general linear constraint satisfaction problems via accelerated gradient descent, enabling differentiable backpropagation and improved GPU perf…

UMOD: a novel multi-objective optimization algorithm efficiently generates uniformly distributed Pareto-optimal solutions by maximizing minimal pairwise distances, providing high-quality representatio…

Unbalanced initializations dramatically accelerate neural network feature learning by modifying the geometry of learning trajectories, enabling faster feature extraction and improved generalization.

Generative adversarial model-based optimization via adaptive source critic regularization (aSCR) significantly boosts offline optimization accuracy.

Learn to project, solve faster! This paper introduces data-driven projections for solving high-dimensional linear programs, proving theoretical guarantees and demonstrating significant improvements in…

New theoretical bounds on Bayesian coreset approximation errors enable efficient large-scale Bayesian inference, overcoming prior limitations and improving coreset construction methods.

This research establishes fundamental convergence properties for the widely-used SAM optimization algorithm, significantly advancing our theoretical understanding and practical applications.

Near-optimal algorithms solve convex simple bilevel problems by reformulating them into functionally constrained problems, achieving near-optimal convergence rates.

FUGAL: a groundbreaking graph alignment method surpassing state-of-the-art accuracy without compromising efficiency by directly aligning adjacency matrices.

A novel framework extends optimization algorithms from linear/quadratic functions to a broader class of ‘upper-linearizable’ functions, providing a unified approach for concave and DR-submodular optim…