Deep Learning
Supplementary: Subsidiary Prototype Alignment for Universal Domain Adaptation
In this appendix, we provide more details of our approach, extensive implementation details, additional analyses, limitations and potential negative societal impact. We summarize the notations used throughout the paper in Table 1. The proposed approach may be unsuitable for datasets with very less number of classes. This might make technology more accessible to organizations and individuals with limited resources. It can also aid applications where data is protected by privacy regulations and hence difficult to collect.
Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation Emmanuel Bengio
This paper is about the problem of learning a stochastic policy for generating an object (like a molecular graph) from a sequence of actions, such that the probability of generating an object is proportional to a given positive reward for that object.
Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress
Equipped with this algorithm, we demonstrate reincarnating RL's gains
GRIN: Generative Relation and Intention Network for Multi-agent Trajectory Prediction Longyuan Li
The prior and recognition model encodes two types of latent codes for each agent: an inter-agent latent code to represent social relations and an intra-agent latent code to represent agent intentions.
Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization
These gains are realized in two frameworks: one is JAX, which provides rich support for these primitives through the XLA compiler.
Multi-Game Decision Transformers
Transformer models offer the best scalability and performance.