Papers
Online Continual Learning with Maximal Interfered Retrieval
Rahaf Aljundi, Eugene Belilovsky, Tinne Tuytelaars et al.
Sequence Modeling with Unconstrained Generation Order
Dmitrii Emelianenko, Elena Voita, Pavel Serdyukov
Bayesian Layers: A Module for Neural Network Uncertainty
Dustin Tran, Mike Dusenberry, Mark van der Wilk et al.
Poisson-Randomized Gamma Dynamical Systems
Aaron Schein, Scott Linderman, Mingyuan Zhou et al.
A Bayesian Theory of Conformity in Collective Decision Making
Koosha Khalvati, Saghar Mirbagheri, Seongmin A. Park et al.
Dying Experts: Efficient Algorithms with Optimal Regret Bounds
Hamid Shayestehmanesh, Sajjad Azami, Nishant A Mehta
Global Convergence of Gradient Descent for Deep Linear Residual Networks
Lei Wu, Qingcan Wang, Chao Ma
Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control
Sai Qian Zhang, Qi Zhang, Jieyu Lin
Learning dynamic polynomial proofs
Alhussein Fawzi, Mateusz Malinowski, Hamza Fawzi et al.
On Distributed Averaging for Stochastic k-PCA
Aditya Bhaskara, Pruthuvi Maheshakya Wijewardena
Learning Sparse Distributions using Iterative Hard Thresholding
Jacky Y Zhang, Rajiv Khanna, Anastasios Kyrillidis et al.
Joint-task Self-supervised Learning for Temporal Correspondence
Xueting Li, Sifei Liu, Shalini De Mello et al.
Probabilistic Logic Neural Networks for Reasoning
Meng Qu, Jian Tang
Statistical-Computational Tradeoff in Single Index Models
Lingxiao Wang, Zhuoran Yang, Zhaoran Wang
Learning Representations for Time Series Clustering
Qianli Ma, Jiawei Zheng, Sen Li et al.
A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment
Felix Leibfried, Sergio Pascual-Díaz, Jordi Grau-Moya
Learning to Perform Local Rewriting for Combinatorial Optimization
Xinyun Chen, Yuandong Tian
Learning Local Search Heuristics for Boolean Satisfiability
Emre Yolcu, Barnabas Poczos
PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
Yikang LI, Tao Ma, Yeqi Bai et al.
Efficiently avoiding saddle points with zero order methods: No gradients required
Emmanouil-Vasileios Vlatakis-Gkaragkounis, Lampros Flokas, Georgios Piliouras
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias
Stéphane d'Ascoli, Levent Sagun, Giulio Biroli et al.
Low-Complexity Nonparametric Bayesian Online Prediction with Universal Guarantees
Alix LHERITIER, Frederic Cazals
CPM-Nets: Cross Partial Multi-View Networks
Changqing Zhang, Zongbo Han, yajie cui et al.
A Simple Baseline for Bayesian Uncertainty in Deep Learning
Wesley J Maddox, Pavel Izmailov, Timur Garipov et al.