Statistical Learning
Examples are not enough, learn to criticize! Criticism for Interpretability
Been Kim, None, Oluwasanmi O. Koyejo
Neural Information Processing Systems http://nips.cc/
Local Similarity-Aware Deep Feature Embedding
Chen Huang, Chen Change Loy, Xiaoou Tang
Neural Information Processing Systems http://nips.cc/
GAP Safe Screening Rules for Sparse-Group Lasso
Eugene Ndiaye, Olivier Fercoq, Alexandre Gramfort, Joseph Salmon
Neural Information Processing Systems http://nips.cc/
Online Convex Optimization with Unconstrained Domains and Losses
Ashok Cutkosky, Kwabena A. Boahen
We propose an online convex optimization algorithm (RESCALEDEXP) that achieves optimal regret in the unconstrained setting without prior knowledge of any bounds on the loss functions. We prove a lower bound showing an exponential separation between the regret of existing algorithms that require a known bound on the loss functions and any algorithm that does not require such knowledge. RESCALEDEXP matches this lower bound asymptotically in the number of iterations. RESCALEDEXP is naturally hyperparameter-free and we demonstrate empirically that it matches prior optimization algorithms that require hyperparameter optimization.
Coevolutionary Latent Feature Processes for Continuous-Time User-Item Interactions
Yichen Wang, Nan Du, Rakshit Trivedi, Le Song
Matching users to the right items at the right time is a fundamental task in recommendation systems. As users interact with different items over time, users' and items' feature may evolve and co-evolve over time. Traditional models based on static latent features or discretizing time into epochs can become ineffective for capturing the fine-grained temporal dynamics in the user-item interactions. We propose a coevolutionary latent feature process model that accurately captures the coevolving nature of users' and items' feature. To learn parameters, we design an efficient convex optimization algorithm with a novel low rank space sharing constraints. Extensive experiments on diverse real-world datasets demonstrate significant improvements in user behavior prediction compared to state-of-the-arts.
Orthogonal Random Features
Felix Xinnan X. Yu, Ananda Theertha Suresh, Krzysztof M. Choromanski, Daniel N. Holtmann-Rice, Sanjiv Kumar
Neural Information Processing Systems http://nips.cc/
The Multiple Quantile Graphical Model
Alnur Ali, J. Zico Kolter, Ryan J. Tibshirani
Neural Information Processing Systems http://nips.cc/
Structured Prediction Theory Based on Factor Graph Complexity
Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Scott Yang
Neural Information Processing Systems http://nips.cc/
Supervised Learning with Tensor Networks
Edwin Stoudenmire, David J. Schwab
Neural Information Processing Systems http://nips.cc/
Learning values across many orders of magnitude
Hado P. van Hasselt, Arthur Guez, Arthur Guez, Matteo Hessel, Volodymyr Mnih, David Silver
Most learning algorithms are not invariant to the scale of the signal that is being approximated. We propose to adaptively normalize the targets used in the learning updates. This is important in value-based reinforcement learning, where the magnitude of appropriate value approximations can change over time when we update the policy of behavior. Our main motivation is prior work on learning to play Atari games, where the rewards were clipped to a predetermined range. This clipping facilitates learning across many different games with a single learning algorithm, but a clipped reward function can result in qualitatively different behavior. Using adaptive normalization we can remove this domain-specific heuristic without diminishing overall performance.