arXiv Machine Learning
Solving Finite-sum Coupled Compositional Optimization via Multi-block-Single-probe Estimator
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 16
SILAGE: Memory-Efficient, Full-Gradient-Free Nonconvex Optimization for Nested Finite Sums
arXiv:2606. 15832v1 Announce Type: new Abstract: Empirical risk minimization on massive datasets naturally exhibits a nested double finite-sum structure, where $N=nm$ total samples are logically or physically partitioned into $n$ blocks of size $m$ (e.
arXiv Machine Learning
Oct 7
A Single-Loop, Constant-Batch First-Order Penalty Method for Stochastic Bilevel Optimization
arXiv:2610.07290v1 Announce Type: cross Abstract: Recent advances in penalty-based methods for stochastic bilevel optimization (SBO) have eliminated the need for second-order derivative oracles. Howe...
arXiv Computer Vision
Aug 26
Adaptive Extrapolated Proximal Gradient Methods with Variance Reduction for Composite Nonconvex Finite-Sum Minimization
arXiv:2502.21099v3 Announce Type: replace-cross Abstract: This paper proposes {\sf AEPG-SPIDER}, an Adaptive Extrapolated Proximal Gradient (AEPG) method with variance reduction for minimizing compos...
arXiv Machine Learning
Oct 12
Stochastic Compositional Optimization via Hybrid Momentum Frank--Wolfe
arXiv:2605. 15350v2 Announce Type: replace-cross Abstract: Stochastic compositional optimization minimizes $F(f(x), x)$ over a compact convex set when the inner map $f$ is available only through noisy samples.
arXiv Machine Learning
Aug 13
Adaptive Bregman Proximal Stochastic Gradient with a Stabilized Barzilai--Borwein Step Size
arXiv:2608. 12009v1 Announce Type: cross Abstract: Bregman proximal stochastic gradient (BPSG) methods bring variance-reduced composite optimization to objectives whose geometry is poorly captured by Euclidean smoothness.
arXiv Machine Learning
Oct 7
From Dual Tracking to Clipping: Provably Faster Distributionally Robust Multi-Objective Optimization
arXiv:2605.05660v3 Announce Type: replace Abstract: Multi-objective optimization (MOO) has received growing attention in applications that require learning under multiple criteria. However, most exis...