Presents classical Õ(n²/ε^{1.5}) and quantum Õ(n/ε^{1.5}) query algorithms for ε-stationary points of twice-differentiable non-convex functions with Lipschitz gradient and Hessian via comparison oracles.
arXiv preprint arXiv:2306.14111 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.LG 5representative citing papers
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
OPRIDE improves query efficiency in offline PbRL via a principled in-dataset exploration strategy and discount scheduling, outperforming prior methods with fewer queries and providing theoretical guarantees.
The paper defines a Gradient Gap for RLVR policy gradients and proves a sharp step-size threshold below which training converges and above which it collapses, with predictions for length and success-rate scaling validated in simulations and on Qwen2.5-Math-7B.
Optimistic regression algorithms with Gibbs updates achieve high-probability KL-regret that degrades gracefully under pointwise KL misspecification for bandits and stagewise KL Bellman misspecification for episodic RL.
citing papers explorer
-
Finding Stationary Points by Comparisons
Presents classical Õ(n²/ε^{1.5}) and quantum Õ(n/ε^{1.5}) query algorithms for ε-stationary points of twice-differentiable non-convex functions with Lipschitz gradient and Hessian via comparison oracles.
-
Convex Optimization for Alignment and Preference Learning on a Single GPU
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
-
OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
OPRIDE improves query efficiency in offline PbRL via a principled in-dataset exploration strategy and discount scheduling, outperforming prior methods with fewer queries and providing theoretical guarantees.
-
On the optimization dynamics of RLVR: Gradient gap and step size thresholds
The paper defines a Gradient Gap for RLVR policy gradients and proves a sharp step-size threshold below which training converges and above which it collapses, with predictions for length and success-rate scaling validated in simulations and on Qwen2.5-Math-7B.
-
Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification
Optimistic regression algorithms with Gibbs updates achieve high-probability KL-regret that degrades gracefully under pointwise KL misspecification for bandits and stagewise KL Bellman misspecification for episodic RL.