الباحثون

Tianbao Yang

المنشورات 2

نسخة أولية وصول مفتوح

A Single-Loop, Constant-Batch First-Order Penalty Method for Stochastic Bilevel Optimization

Xingyu Chen, Ming Yang, Quanqi Hu وآخرون · 2026

Recent advances in penalty-based methods for stochastic bilevel optimization (SBO) have eliminated the need for second-order derivative oracles. However, for stochastic nonconvex-strongly convex bilevel problems, existing first-order methods typically rely on nested loops and/or large batch sizes for attaining $O(ε^{-6 …

نسخة أولية وصول مفتوح

From Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model

Vicente Balmaseda, Ching-Long Lin, Tianbao Yang · 2026

Strong image generation models are conditioned on class labels, aligned to frozen pretrained encoders, or built on separately trained autoencoders. While effective, generation then depends on supervision or pretraining: labels must be annotated, and encoders or autoencoders pretrained for the target domain. We study jo …

المؤلفون المشاركون