Europe
On Fast Leverage Score Sampling and Optimal Learning
Alessandro Rudi, Daniele Calandriello, Luigi Carratino, Lorenzo Rosasco
Neural Information Processing Systems http://nips.cc/
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.
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.
Reinforcement Learning of Theorem Proving
Cezary Kaliszyk, Josef Urban, Henryk Michalewski, Miroslav Olลกรกk
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.
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.
Latent Field Discovery In Interacting Dynamical Systems With Neural Fields
Systems of interacting objects often evolve under the influence of field effects that govern their dynamics, yet previous works have abstracted away from such effects, and assume that systems evolve in a vacuum. In this work, we focus on discovering these fields, and infer them from the observed dynamics alone, without directly observing them.
A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training
However, the training of a sparse DNN encounters great challenges in achieving optimal generalization ability despite the efforts from the state-of-the-art sparse training methodologies. To unravel the mysterious reason behind the difficulty of sparse training, we connect network sparsity with the structure of neural loss functions and identify that the cause of such difficulty lies in a chaotic loss surface.
Monte-Carlo Tree Search for Constrained POMDPs
Jongmin Lee, Geon-hyeong Kim, Pascal Poupart, Kee-Eung Kim
Neural Information Processing Systems http://nips.cc/