2021-12
Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
2021-10
Compositional Attention: Disentangling Search and Retrieval
2021-09
Exploring the Optimality of Tight-Frame Scattering Networks
Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers
2021-08
Approximate Bayesian Optimisation for Neural Networks
Toward Optimal Solution for the Context-Attentive Bandit Problem.
Sequoia: A Software Framework to Unify Continual Learning Research
2021-07
Learning Brain Dynamics With Coupled Low-Dimensional Nonlinear Oscillators and Deep Recurrent Networks.
Parametric Scattering Networks.
2021-06
Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Toward Skills Dialog Orchestration with Online Learning
Double-Linear Thompson Sampling for Context-Attentive Bandits
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
Continual Learning in Deep Networks: an Analysis of the Last Layer
2021-05
Adversarial Feature Desensitization
Predicting Infectiousness for Proactive Contact Tracing
2021-04
Gradient Masked Federated Optimization.
Towards Causal Federated Learning For Enhanced Robustness and Privacy.
Understanding Continual Learning Settings with Data Distribution Drift Analysis.
2021-01
Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL
2020-12
Towards Continual Reinforcement Learning: A Review and Perspectives.
2020-10
COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing.
Predicting Infectiousness for Proactive Contact Tracing
2020-07
Survey on Applications of Multi-Armed and Contextual Bandits
2020-06
Chaotic Continual Learning
Adversarial Feature Desensitization
2020-05
COVI White Paper.
An Empirical Study of Human Behavioral Agents in Bandits, Contextual Bandits and Reinforcement Learning
Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL
A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry
2020-04
2020-03
Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation
2020-01
Resting-state connectivity stratifies premanifest Huntington's disease by longitudinal cognitive decline rate.
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
Publications collected and formatted using Paperoni