Transformers have significantly impacted domains like natural language processing,
computer vision, and robotics, where they improve performance compared to other neural …

Similar to humans, RL agents use interactive learning to successfully obtain satisfactory
decision strategies. However, in many cases, it is desirable to learn directly from …

Neural approaches for combinatorial optimization (CO) equip a learning mechanism to
discover powerful heuristics for solving complex real-world problems. While neural …

Abstract The well-known Gumbel-Max trick for sampling from a categorical distribution can
be extended to sample $ k $ elements without replacement. We show how to implicitly apply …

Approximate nearest neighbour search (ANNS) in high-dimensional space is an essential
and fundamental operation in many applications from many domains such as multimedia …

We study a synthetic corpus based approach for language models (LMs) to acquire logical
deductive reasoning ability. The previous studies generated deduction examples using …

Retrieving relevant targets from an extremely large target set under computational limits is a
common challenge for information retrieval and recommendation systems. Tree models …

Search is an important technique in program synthesis that allows for adaptive strategies
such as focusing on particular search directions based on execution results. Several prior …

We derive an unbiased estimator for expectations over discrete random variables based on
sampling without replacement, which reduces variance as it avoids duplicate samples. We …

We focus on Maximum Inner Product Search (MIPS), which is an essential problem in many
machine learning communities. Given a query, MIPS finds the most similar items with the …