Code generation is typically trained in the primal space of programs: a model produces a candidate solution and receives sparse execution feedback, often a single pass/fail bit. Test-time scaling enriches the inference procedure by sampling multiple candidates and judging among them, but the comparative information this process reveals is discarded after inference. We argue that this information defines a dual judgment space that provides a far richer training signal: the model learns not from an isolated success or failure, but from the relative correctness structure across its own plausible attempts, identifying which succeed, which fail, and what distinguishes them. We introduce DuST (Dual Self-Training), a framework for self-training from the dual judgment space. DuST samples candidate programs from the model's own distribution, labels them through sandbox execution, retains groups containing both successes and failures, and trains the model to rank candidates by execution correctness using GRPO. The objective is purely discriminative: the model is never directly rewarded for generating correct programs. Dual self-training improves both judgment and generation. Across five models spanning two families and three scales (4B to 30B), DuST consistently improves Best-of-4 test-time scaling on LiveCodeBench. For Qwen3-30B-Thinking on LiveCodeBench v6, judgment quality improves by +6.2 NDCG, single-sample pass@1 improves by +3.1, and Best-of-4 accuracy improves by +4.1. The trained model's single rollout matches the base model's Best-of-4 performance. SFT on the same ranking data improves judgment without improving generation, confirming that on-policy RL is the mechanism that transfers dual-space learning back into primal generation.
Stochastic Primal Dual Coordinate Method with Non-Uniform Sampling Based on Optimality Violations
Nagoya Institute of Technology(名古屋工业大学);RIKEN Center for Advanced Intelligence Project(理化学研究所革新智能综合研究中心);National Institute for Materials Science(国立材料科学研究所)
Online Primal-Dual Algorithms with Predictions for Packing Problems
University Paris-Saclay(巴黎萨克雷大学);Sorbonne University(巴黎索邦大学);IBISC(IBISC(需注意:IBISC是巴黎萨克雷大学下属研究机构,此处按原文提取));CNRS(法国国家科学研究中心);LIP6(LIP6(巴黎索邦大学下属实验室,此处按原文提取))
Random extrapolation for primal-dual coordinate descent
EPFL(洛桑联邦理工学院);Télécom Paris(巴黎电信学院);Institut Polytechnique de Paris(巴黎综合理工学院)
我们引入了一种随机外推的原始-对偶坐标下降法,该方法适应于数据矩阵的稀疏性和目标函数的有利结构。我们的方法只更新原始和对偶变量的一个子集与稀疏的数据,它使用大的步长与密集的数据,保留的好处,为每种情况下设计的具体方法。除了适应稀疏性,我们的方法达到快速收敛的保证在有利的情况下\textit{without any modifications}。特别地,我们证明了度量次正则下的线性收敛性,它适用于强凸-强凹问题和分段线性二次函数。在一般的凸-凹情形下,我们证明了序列的几乎必然收敛和原始-对偶间隙和目标值的最佳次线性收敛速度。数值证据证明了我们的方法在稀疏和密集环境中的最先进的经验性能,匹配和改进了现有的方法。
本文考虑凸-凹鞍点问题$\min_{x}\max_{y} f(x)+y^\top A x-g(y)$,其中$f$是光滑凸的,$g$是光滑强凸的.证明了当耦合矩阵$A$具有满列秩时,即使$f$不是强凸的,vanilla原-对偶梯度法也能达到线性收敛.我们的结果推广了以前的工作,要么要求$f$和$g$是二次函数,或要求$f$和$g$的邻近映射。我们采用了一种新的分析技术,在每次迭代中使用“鬼”更新作为参考,并显示在原始-对偶梯度法的迭代收敛到这个“鬼”序列。利用同样的技巧,我们进一步分析了具有有限和结构的凸凹鞍点问题的原始-对偶随机方差约减梯度(SVRG)方法。