Pith. sign in

REVIEW 1 cited by

Reinforcement Learning and Adaptive Sampling for Optimized DNN Compilation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1905.12799 v1 pith:JPFKWTMP submitted 2019-05-30 cs.LG stat.ML

classification cs.LGstat.ML
keywords samplingadaptivenetworkstimecompilationlearningneuralreinforcement
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Achieving faster execution with shorter compilation time can enable further diversity and innovation in neural networks. However, the current paradigm of executing neural networks either relies on hand-optimized libraries, traditional compilation heuristics, or very recently, simulated annealing and genetic algorithms. Our work takes a unique approach by formulating compiler optimizations for neural networks as a reinforcement learning problem, whose solution takes fewer steps to converge. This solution, dubbed ReLeASE, comes with a sampling algorithm that leverages clustering to focus the costly samples (real hardware measurements) on representative points, subsuming an entire subspace. Our adaptive sampling not only reduces the number of samples, but also improves the quality of samples for better exploration in shorter time. As such, experimentation with real hardware shows that reinforcement learning with adaptive sampling provides 4.45x speed up in optimization time over AutoTVM, while also improving inference time of the modern deep networks by 5.6%. Further experiments also confirm that our adaptive sampling can even improve AutoTVM's simulated annealing by 4.00x.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ReLATE: Learning Efficient Sparse Encoding for High-Performance Tensor Decomposition

    cs.LG 2025-08 conditional novelty 6.0 of 10

    A DRL agent learns bit-interleaving patterns for sparse tensor storage, delivering 1.4 to 1.46x geometric-mean speedups for tensor decomposition over expert formats.

Pith tools