Country
LiftingWeakSupervisionToStructuredPrediction
For labels taking values in a finite metric space, we introduce techniques new to weak supervision based on pseudo-Euclidean embeddings andtensor decompositions, providing anearly-consistent noise rate estimator.
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
Aiming to address this limitation, we present Easy2Hard-Bench, a consistently formatted collection of 6 benchmark datasets spanning various domains, such as mathematics and programming problems, chess puzzles, and reasoning questions.
Accelerating SGD for Highly Ill-Conditioned Huge-Scale Online Matrix Completion
Gavin Zhang, University of Illinois at Urbana–Champaign, jialun2@illinois.edu, "3026 Hong-Ming Chiu, University of Illinois at Urbana–Champaign, hmchiu2@illinois.edu, "3026 Richard Y. Zhang, University of Illinois at Urbana–Champaign, ryz@illinois.edu
Accelerating SGD for Highly Ill-Conditioned Huge-Scale Online Matrix Completion
Gavin Zhang, University of Illinois at Urbana–Champaign, jialun2@illinois.edu, "3026 Hong-Ming Chiu, University of Illinois at Urbana–Champaign, hmchiu2@illinois.edu, "3026 Richard Y. Zhang, University of Illinois at Urbana–Champaign, ryz@illinois.edu
Reinforcement Learning of Theorem Proving
Cezary Kaliszyk, Josef Urban, Henryk Michalewski, Miroslav Olšák
In practice, today's best ATP system are however still far weaker than trained mathematicians in most research domains. Machine learning from many proofs could be used to improveonthis.
Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller
Pratyusha Sharma, Deepak Pathak, Abhinav Gupta
Neural Information Processing Systems http://nips.cc/
Discrimination-aware Channel Pruning for Deep Neural Networks
Zhuangwei Zhuang, Mingkui Tan, Bohan Zhuang, Jing Liu, Yong Guo, Qingyao Wu, Junzhou Huang, Jinhui Zhu
Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, whilst the latter kind optimizes the reconstruction error but ignores the discriminative power of channels.
Posterior Collapse of a Linear Latent Variable Model
This work identifies the existence and cause of a type of posterior collapse that frequently occurs in the Bayesian deep learning practice. For a general linear latent variable model that includes linear variational autoencoders as a special case, we precisely identify the nature of posterior collapse to be the competition between the likelihood and the regularization of the mean due to the prior. Our result suggests that posterior collapse may be related to neural collapse and dimensional collapse and could be a subclass of a general problem of learning for deeper architectures.