Philip Bachman
15 papers · 2014–2023 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Interdisciplinary Bridge π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer π Conference Polyglot (5)
π£
Hot Topic Early Bird
π
Cross-Pollinator
(13)
π
Conference Polyglot
(5)
π
Triple Crown
π§¬
Topic Evolution
π
Century Club
(15)
π
Trend Setter
ποΈ
Keyword Collector
(54)
π₯
Unstoppable
(8)
Conferences
NIPS (7)
ICML (5)
ACL (1)
EMNLP (1)
ICLR (1)
Top co-authors
Keywords
representation learning
(5)
generative model
(3)
mutual information
(2)
contrastive learning
(2)
variational inference
(2)
continual learning
(1)
reinforcement learning
(1)
deep reinforcement learning
(1)
hierarchical model
(1)
sentiment analysis
(1)
function approximation
(1)
model robustness
(1)
sequential decision making
(1)
self-supervised learning
(1)
markov decision process
(1)
image generation
(1)
image translation
(1)
image reconstruction
(1)
semi-supervised learning
(1)
active learning
(1)
Papers
Ignorance is Bliss: Robust Control via Information Gating
NIPS 2023
Decomposed Mutual Information Estimation for Contrastive Representation Learning
ICML 2021
Data-Efficient Reinforcement Learning with Self-Predictive Representations
ICLR 2021
Pretraining Representations for Data-Efficient Reinforcement Learning
NIPS 2021
Deep Reinforcement and InfoMax Learning
NIPS 2020
Learning Representations by Maximizing Mutual Information Across Views
NIPS 2019
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
ICML 2018
Learning Algorithms for Active Learning
ICML 2017
A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data
ACL 2016
An Architecture for Deep, Hierarchical Generative Models
NIPS 2016
Natural Language Comprehension with the EpiReader
EMNLP 2016
Variational Generative Stochastic Networks with Collaborative Shaping
ICML 2015
Data Generation as Sequential Decision Making
NIPS 2015
Sample-based approximate regularization
ICML 2014
Learning with Pseudo-Ensembles
NIPS 2014