20 results for “Convex optimization”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper provides a new method for online inventory optimization with convex capacity sets that improves the best known regret guarantee.
This paper proposes new methods for bilevel optimization in machine learning tasks.
This paper improves the worst-case regret in Online Convex Optimization (OCO) by introducing a unified probing model with a budget of pairwise probes.
This paper establishes a direct connection between Approximate Message Passing (AMP) and the Convex Gaussian Min-max Theorem (CGMT) for regularized linear regression and M-estimation.
This paper shows that stochastic nonconvex optimization can be reduced to ordinary static regret minimization in online convex optimization, and establishes convergence rates for smooth and Lipschitz…
This paper introduces Curvature-Weighted Gradient Diversity (CWGD), a geometry-aware measure for optimization noise that reduces the asymptotic optimization error floor by up to a factor of two compar…
This paper proves the conjecture that Local SGD outperforms Mini-batch SGD under bounded second-order heterogeneity for general convex objectives, improving the convergence guarantee and lower bounds.
This paper proposes a one-trial proximal algorithm for minimizing nonsmooth, nonconvex objectives with unknown weak-convexity parameter.
The paper establishes a lower bound for the improvement of linear dependence on the restricted condition number in sparse convex optimization, using the Small-Set Expansion Hypothesis.
Cheng-Han Huang, Yongliang Sun, Chaoyan Huang, Ismail Alkhouri +1 more
The paper establishes conditions for QUBO formulations of combinatorial optimization problems that guarantee valid binary and feasible local minimizers using gradient-based methods.
The paper improves the optimization problem at the core of the laser method for obtaining matrix multiplication bounds, yielding a new upper bound of ω < 2.371177.
This paper reviews models of inexact computational oracles in smooth continuous optimization and their implications for optimization algorithms.
A new algorithm is proposed for approximating solutions to linear-multi-parametric optimization problems with negative parameter dependencies and non-fixed parameter sets.
The paper characterizes the minimax optimal excess-risk rate for pure $\varepsilon$-DP stochastic convex optimization with heavy-tailed gradients, providing an algorithm that achieves this rate.
This paper constructs an epsilon-cover of the joint value set of m constant-degree polynomials over a convex set H in the linfty-norm, with size n^(O(log(mn)/ε^2)), given that the polynomials have a c…