← Back to all news
arXiv AI By M. Harper Langston, Pierre-David Letourneau, Dalton Jones, Roland Memisevic, Peter Scott, Mingu Lee, Richard A. Lethin, Christopher Lott, Fatih Porikli, Harris Teague

Multiplicative vs. Additive State Coupling in Learned Optimizer Schedules

Read the original on arXiv AI →

The paper studies learned schedules for a continuous penalty relaxation of the MAX-CUT problem by backpropagating through an unrolled classical solver. It compares three architectural variants: a state‑blind schedule, a state‑adaptive bilinear schedule, and an additive ablation. The bilinear schedule generalizes well to larger, out‑of‑distribution instances and outperforms its untrained baseline, whereas the additive model performs similarly to the bilinear model on‑distribution but fails to generalize out‑of‑distribution.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 15

Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards

The paper investigates reinforcement learning with verifiable rewards (RLVR), where costly model-generated responses encourage larger rollout batches and a square‑root learning‑rate scaling. Using a two‑clock framework, the authors show that while the square‑root rule preserves first‑order drift per sample, larger batches suffer from curvature losses, leading to a critical batch size beyond which sample efficiency degrades. Experiments on Qwen2.5‑Math‑1.5B confirm the predicted progress gap and failure clock, and the authors propose a simple multi‑step RLVR schedule that starts below the critical batch and switches to a larger batch before failure.

By Yuante Li, Junwei Quan, Kai Qiu, Kate Zhang, Yicheng Tao
reinforcement-learning
More like this →
arXiv Machine Learning
Sep 22

When Is Availability-Aware Training Worth It? A Benchmark and Empirical Study of Interruption-Resilient Optimization Under Predictable Compute Schedules

The paper introduces OrbitTrace, a benchmark of 50 physics‑grounded compute‑availability traces from satellite orbits, and investigates whether specialized interruption‑resilient optimizers are needed when training is interrupted by predictable compute gaps. Experiments on CIFAR‑10/ResNet‑18 and GPT‑2/AdamW show that a strong checkpoint‑and‑resume baseline that preserves full optimizer state and indexes learning‑rate schedules in effective time matches uninterrupted training, rendering most availability‑aware methods unnecessary. Only in a narrow regime—large models with non‑persistable optimizer state and frequent short pauses—does reactive adaptation recover a modest portion of the state‑loss penalty, and even this benefit disappears for eclipse‑scale gaps.

By Subhadip Mitra
llmsbenchmarks
More like this →
arXiv Machine Learning
Sep 10

Spectral Prioritized Sweeping in Nonstationary Reinforcement Learning

Spectral Prioritized Sweeping (SPS) extends traditional Prioritized Sweeping by incorporating graph topology through the resolvent and Laplacian diffusion, creating a smoother priority score that propagates reward changes more effectively in nonstationary reinforcement learning. The method, called Graph Topology Augmentation for Prioritized Sweeping (GTA-PS), uses a mixing of regularized Laplacian inverses and an adaptive scheduler based on the Second Largest Eigenvalue Modulus to adjust the influence of topology during replanning. Experiments on FourRooms and GARNET domains show that GTA-PS improves replanning efficiency compared to standard PS under both exact dynamic programming and Dyna-style planners.

By Hung Pham, Tuan Dam
diffusionreinforcement-learning
More like this →