Search Results for author: Robert Kirby

Found 9 papers, 4 papers with code

PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning

no code implementations14 May 2022 Rajarshi Roy, Jonathan Raiman, Neel Kant, Ilyas Elkin, Robert Kirby, Michael Siu, Stuart Oberman, Saad Godil, Bryan Catanzaro

Deep Convolutional RL agents trained on this environment produce prefix adder circuits that Pareto-dominate existing baselines with up to 16. 0% and 30. 2% lower area for the same delay in the 32b and 64b settings respectively.

reinforcement-learning

Meta-Learning with Adjoint Methods

no code implementations16 Oct 2021 Shibo Li, Zheng Wang, Akil Narayan, Robert Kirby, Shandian Zhe

Despite its success, a critical challenge in MAML is to calculate the gradient w. r. t the initialization of a long training trajectory for the sampled tasks, because the computation graph can rapidly explode and the computational cost is very expensive.

Meta-Learning

Guiding Global Placement With Reinforcement Learning

no code implementations6 Sep 2021 Robert Kirby, Kolby Nottingham, Rajarshi Roy, Saad Godil, Bryan Catanzaro

In this work we augment state-of-the-art, force-based global placement solvers with a reinforcement learning agent trained to improve the final detail placed Half Perimeter Wire Length (HPWL).

reinforcement-learning

Physics Informed Deep Kernel Learning

no code implementations8 Jun 2020 Zheng Wang, Wei Xing, Robert Kirby, Shandian Zhe

Deep kernel learning is a promising combination of deep neural networks and nonparametric function learning.

Gaussian Processes

Multi-Fidelity High-Order Gaussian Processes for Physical Simulation

1 code implementation8 Jun 2020 Zheng Wang, Wei Xing, Robert Kirby, Shandian Zhe

To address these issues, we propose Multi-Fidelity High-Order Gaussian Process (MFHoGP) that can capture complex correlations both between the outputs and between the fidelities to enhance solution estimation, and scale to large numbers of outputs.

Gaussian Processes

SDCNet: Video Prediction Using Spatially-Displaced Convolution

1 code implementation2 Nov 2018 Fitsum A. Reda, Guilin Liu, Kevin J. Shih, Robert Kirby, Jon Barker, David Tarjan, Andrew Tao, Bryan Catanzaro

We present an approach for high-resolution video frame prediction by conditioning on both past frames and past optical flows.

Optical Flow Estimation SSIM +1

Large Scale Language Modeling: Converging on 40GB of Text in Four Hours

1 code implementation3 Aug 2018 Raul Puri, Robert Kirby, Nikolai Yakovenko, Bryan Catanzaro

We provide a learning rate schedule that allows our model to converge with a 32k batch size.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.