Search Results for author:
Found 7 papers, 4 papers with code
Solving MaxSAT with Matrix Multiplication
Since matrix multiplication is the main computational primitive for block Gibbs sampling in an RBM, our approach leads to an elegantly simple algorithm (40 lines of JAX) well-suited for neural network accelerators.
Competition-Level Code Generation with AlphaCode
Programming is a powerful and ubiquitous problem-solving tool.
Ranked #1 on
Code Generation
on CodeContests
Perceiver: General Perception with Iterative Attention
The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models.
Ranked #29 on
Audio Classification
on AudioSet
Solving Mixed Integer Programs Using Neural Networks
Our approach constructs two corresponding neural network-based components, Neural Diving and Neural Branching, to use in a base MIP solver such as SCIP.
Strong Generalization and Efficiency in Neural Programs
We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction.
Prioritized Unit Propagation with Periodic Resetting is (Almost) All You Need for Random SAT Solving
We share this observation in the hope that it helps the SAT community better understand the hardness of random instances used in competitions and inspire other interesting ideas on SAT solving.
Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs
We present a deep reinforcement learning approach to minimizing the execution cost of neural network computation graphs in an optimizing compiler.
