N Wu, Y Xie - ACM Computing Surveys (CSUR), 2022 - dl.acm.org
It has been a long time that computer architecture and systems are optimized for efficient execution of machine learning (ML) models. Now, it is time to reconsider the relationship …
DP Bertsekas - European journal of control, 2005 - Elsevier
We survey some recent research directions within the field of approximate dynamic programming, with a particular emphasis on rollout algorithms and model predictive control …
S Whiteson - Journal of Machine Learning Research, 2006 - jmlr.org
Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning …
A Fern, S Yoon, R Givan - Advances in neural information …, 2003 - proceedings.neurips.cc
We explore approximate policy iteration, replacing the usual costfunction learning step with a learning step in policy space. We give policy-language biases that enable solution of very …
M Trofin, Y Qian, E Brevdo, Z Lin… - arXiv preprint arXiv …, 2021 - arxiv.org
Leveraging machine-learning (ML) techniques for compiler optimizations has been widely studied and explored in academia. However, the adoption of ML in general-purpose …
C Mendis, C Yang, Y Pu… - Advances in Neural …, 2019 - proceedings.neurips.cc
Modern microprocessors are equipped with single instruction multiple data (SIMD) or vector instruction sets which allow compilers to exploit fine-grained data level parallelism. To …
DP Bertsekas - Handbook of combinatorial optimization, 2013 - mit.edu
This chapter discusses rollout algorithms, a sequential approach to optimization problems, whereby the optimization variables are optimized one after the other. A rollout algorithm …
The ability to create and to use abstractions in complex environments, that is, to systematically ignore irrelevant details, is a key reason that humans are effective problem …
Instruction scheduling is a compiler optimization that can improve program speed, sometimes by 10% or more, but it can also be expensive. Furthermore, time spent optimizing …