Enhong Chen

Yuanhao Pu, Defu Lian, Enhong Chen

The Softmax loss is one of the most widely employed surrogate objectives for classification and ranking tasks. To elucidate its theoretical properties, the Fenchel-Young framework situates it as a canonical instance within a broad family of surrogates. Concurrently, another line of research has addressed scalability when the number of classes is exceedingly large, in which numerous approximations have been proposed to retain the benefits of the exact objective while improving efficiency. Building on these two perspectives, we present a principled investigation of the Softmax-family losses. We examine whether different surrogates achieve consistency with classification and ranking metrics, and analyze their gradient dynamics to reveal distinct convergence behaviors. We also introduce a systematic bias-variance decomposition for approximate methods that provides convergence guarantees, and further derive a per-epoch complexity analysis, showing explicit trade-offs between effectiveness and efficiency. Extensive experiments on a representative task demonstrate a strong alignment between consistency, convergence, and empirical performance. Together, these results establish a principled foundation and offer practical guidance for loss selections in large-class machine learning applications.

Hong Xie, Xiao Hu, Tao Tan et al.

The reinforcement fine-tuning area is undergoing an explosion papers largely on optimizing design choices. Though performance gains are often claimed, inconsistent conclusions also arise from time to time, making the progress illusive. Reflecting on this illusion, we still lack principled answers to two fundamental questions: 1) what is the role of each design choice? 2) which ones are critical? This paper aims to shed light on them. The underlying challenge is that design choices are entangled together, making their contribution to learning and generalization difficult to attribute. To address this challenge, we first construct a minimalist baseline for disentangling factors: one rollout per query in each round, the outcome reward serving as the training signal without any advantage trick, and a batch size of thirty-two. This baseline connects to batched contextual bandit learning, which facilitates experimental analysis. Centering around this baseline, we design an experiment pipeline, examining the marginal gains of factors like advantage, number of rollouts, etc. Experiments on three base models and two datasets, not only reveal new understanding on the role of various design choices on learning and generalization dynamics, but also identify critical ones that deserve more effort.