Beyond Throughput and Compression Ratios: Towards High End-to-end Utility of Gradient Compressionby Wenchen Han, Shay…
Contractual Reinforcement Learning: Pulling Arms with Invisible Handsby Jibang Wu, Siyu Chen, Mengdi Wang, Huazheng…
On Implications of Scaling Laws on Feature Superpositionby Pavan KattaFirst submitted to arxiv on: 1…
Scalable Nested Optimization for Deep Learningby Jonathan LorraineFirst submitted to arxiv on: 1 Jul 2024CategoriesMain:…
Revisiting Random Walks for Learning on Graphsby Jinwoo Kim, Olga Zaghen, Ayhan Suleymanzade, Youngmin Ryou,…
Physics-Inspired Deep Learning and Transferable Models for Bridge Scour Predictionby Negin Yousefpour, Bo WangFirst submitted…
Evaluating Model Performance Under Worst-case Subpopulationsby Mike Li, Hongseok Namkoong, Shangzhou XiaFirst submitted to arxiv…
Deep Reinforcement Learning for Adverse Garage Scenario Generationby Kai LiFirst submitted to arxiv on: 1…
Overcoming Common Flaws in the Evaluation of Selective Classification Systemsby Jeremias Traub, Till J. Bungert,…
On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)by Jerry Yao-Chieh Hu,…