Sample-Efficient Optimization in the Latent Space of Deep Generative - PowerPoint PPT Presentation

Jun 24, 2023 •236 likes •292 views

Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining Erik Daxberger, Austin Tripp & Jos e Miguel Hern andez-Lobato RealML @ ICML2020 2020-07-18 Problem Optimization of expensive,

Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining Erik Daxberger*, Austin Tripp* & Jos´ e Miguel Hern´ andez-Lobato RealML @ ICML2020 2020-07-18
Problem Optimization of expensive, black box functions on structured input spaces. Examples: Drug Design Materials Discovery Neural Architecture Search Erik Daxberger*, Austin Tripp* & Jos´ e Miguel Hern´ andez-Lobato Keyword: Weighted Retraining 2/4
Latent Space Optimization Optimize in the latent space Z of a deep generative model (instead of data space X ) X X X X Z Z Z Z Normal With weighted retraining Erik Daxberger*, Austin Tripp* & Jos´ e Miguel Hern´ andez-Lobato Keyword: Weighted Retraining 3/4
Results Chemical Design Task weight; retrain 20 weight; no retrain no weight; retrain works with a variety of models no weight; no retrain 15 original easy to implement 10 huge increase in performance and sample efficiency 5 0 0 100 200 300 400 500 Number of objective function evaluations More results in the paper! Erik Daxberger*, Austin Tripp* & Jos´ e Miguel Hern´ andez-Lobato Keyword: Weighted Retraining 4/4

Download Presentation

Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Empirical Analysis of Latent Space Embedding David Mount and Eunhui Park Department of Computer

Latent Space Embeddings Optimization Exploration Tool Empirical Analysis of Latent Space Embedding David Mount and Eunhui Park Department of Computer Science University of Maryland, College Park MURI Meeting June 3, 2011 Latent Space

204 views • 17 slides

Graph Sketching, Sampling, Streaming, and Space Efficient Optimization (Part II) Sudipto Guha

Graph Sketching, Sampling, Streaming, and Space Efficient Optimization (Part II) Sudipto Guha and Andrew McGregor Space Efficient Optimization for Graphs Impact of Dimensionality Reduction, Embeddings, L p L q , etc. Thesis : Graph

2.3k views • 198 slides

Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model CS330

Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model CS330 Student Presentation Table of Contents Motivation & problem Method overview Experiments Takeaways Discussion (strengths

653 views • 24 slides

Optimization-Based Model Fitting for Latent Class and Latent Profile Analyses Guan-Hua Huang,

Optimization-Based Model Fitting for Latent Class and Latent Profile Analyses Guan-Hua Huang, Su-Mei Wang and Chung-Chu Hsu 12/17/2010 Breast cancer data van't Veer et al . Nature 2002 The 78 sporadic lymph-node-negative breast cancer

358 views • 24 slides

Space: Space: System Architecture System Architecture vs Optimization vs Optimization

Space: Space: System Architecture System Architecture vs Optimization vs Optimization Vladimir Grebenyuk Raytheon Canada Limited Space: The Space: The First Steps First Steps October 4,1957 April 12, 1961 July 20,

819 views • 52 slides

DeepMDP Learning Latent Space Continuous Models for Representation Learning Carles Gelada,

DeepMDP Learning Latent Space Continuous Models for Representation Learning Carles Gelada, Saurabh Kumar, Jacob Buckman, Ofir Nachum, Marc G. Bellemare Simple Representations for RL 2 12 DeepMDP Latent Space Model: Neural networks MDP:

573 views • 17 slides

Efficient Model Evaluation in the Search-Based Approach to Latent Structure Discovery Tao Chen,

Efficient Model Evaluation in the Search-Based Approach to Latent Structure Discovery Tao Chen, Nevin L. Zhang and Yi Wang Department of Computer Science & Engineering The Hong Kong University of Science & Technology 1 Latent Tree

595 views • 25 slides

and Hash Coding with Deep Neural Networks Presenter: MinKu Kang 1 Why did I choose this paper?

Simultaneous Feature Learning and Hash Coding with Deep Neural Networks Presenter: MinKu Kang 1 Why did I choose this paper? Efficient image retrieval via binary encoding of images - efficient bitwise operations. - space-efficient

606 views • 36 slides

Relational Deep Learning: A Deep Latent Variable Model for Link Prediction Hao Wang, Xingjian

Relational Deep Learning: A Deep Latent Variable Model for Link Prediction Hao Wang, Xingjian Shi, Dit-Yan Yeung Motivation Bayesian Deep Learning Relational Deep Learning Parameter Learning Experiments Conclusion

577 views • 40 slides

Space-efficient quantum Space-efficient quantum automata automata Andris Ambainis Nikolay

Space-efficient quantum Space-efficient quantum automata automata Andris Ambainis Nikolay Nahimov Department of Computer Science University of Latvia TQC 2008 Quantum Finite Automata Mathematical model for quantum computers with

616 views • 29 slides

An Efficient Posterior Regularized Latent Variable Model for Interactive Sound Source

An Efficient Posterior Regularized Latent Variable Model for Interactive Sound Source Separation Nicholas J. Bryan, Stanford University Gautham J. Mysore, Adobe Research ICML 2013 Sound Check 1 Motivation I Real world

465 views • 21 slides

review and more examples Sample space: S = set of all potential outcomes of experiment E.g., flip

review and more examples Sample space: S = set of all potential outcomes of experiment E.g., flip two coins: S = {(H,H), (H,T), (T,H), (T,T)} Events: E S is an arbitrary subset of the sample space 1 head in 2 flips: E = {(H,H), (H,T),

493 views • 20 slides

Probability Definitions Probability Space : ordered triple ( , F , P ). ( Sample Space )

Probability Definitions Probability Space : ordered triple ( , F , P ). ( Sample Space ) is a set (possible outcomes); elements are called elementary outcomes. F is a family of subsets ( events ) of with the property that F

296 views • 6 slides

Null Space Gradient Flows for Constrained Optimization with Applications to Shape Optimization

Null Space Gradient Flows for Constrained Optimization with Applications to Shape Optimization Florian Feppon Gr egoire Allaire, Charles Dapogny Julien Cortial, Felipe Bordeu SIAM CSE Spokane February 26, 2019 Shape optimization

693 views • 42 slides

Primary reference: Casella-Berger 2 nd Edition Presentation 1-1-1: The Sample Space and Events

Presentation 1-1-1: The Sample Space and Events Primary reference: Casella-Berger 2 nd Edition Presentation 1-1-1: The Sample Space and Events (the sample space) And in it were (of an experiment) 2 Presentation 1-1-1: The Sample Space

333 views • 11 slides

Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan

Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan Zelener Machine Learning Reading Group January 7 th 2016 The Graduate Center, CUNY Objectives Explain some of the trends of deep learning and

680 views • 44 slides

Combining Text and Image Processing in an Automa6c Image

Combining Text and Image Processing in an Automa6c Image Annota6on System Iulian Ilie (SHSS, Jacobs University) Joint work with Arne Jacobs, OFhein

275 views • 23 slides

Security for Cloud & Big Data CS 161: Computer Security Prof. David Wagner April 18, 2013

Bitcoin, Security for Cloud & Big Data CS 161: Computer Security Prof. David Wagner April 18, 2013 Bitcoin Public, distributed, peer-to-peer, hash-chained audit log of all transactions (block chain). Mining: Each entry in block

499 views • 24 slides

A Model for Recommending Research Articles: A Case Study in Computer Science, Neuroscience and

A Model for Recommending Research Articles: A Case Study in Computer Science, Neuroscience and Biology Nuhi BESIMI, Betim IO, Adrian BESIMI 1 Outline Introduction Research Problem The Proposed Model A Case Study in Computer

344 views • 33 slides

Argument Retrieval in Project Debater Yufang Hou IBM Research Europe, Dublin IBM Research:

Argument Retrieval in Project Debater Yufang Hou IBM Research Europe, Dublin IBM Research: History of Grand Challenges 2019 First computer to successfully debate champion debaters 2011 ( Proje ater ) Project Debat First computer to defeat

951 views • 27 slides

Optimizing Parallel Reduction in CUDA Mark Harris NVIDIA Developer Technology

Optimizing Parallel Reduction in CUDA Mark Harris NVIDIA Developer Technology http://developer.download.nvidia.com/assets/cuda/files/reduction.pdf Tuesday, September 11, 12 Parallel Reduction Tree-based approach used within each thread block

669 views • 39 slides

A Keyword-based ICN-IoT Platform Function tag Hashtags des Hierarchical Part z }| { z}|{ z }|

A Keyword-based ICN-IoT Platform Function tag Hashtags des Hierarchical Part z }| { z}|{ z }| { cation- /a/b/c/ f:tag #tag1, #tag2 | {z } | {z } | {z } describe Domain location Network function IoT information Figure 1:

390 views • 15 slides

For Tuesday: Finish HW5 "Become a Requester" (Warning: you need to register as a

For Tuesday: Finish HW5 "Become a Requester" (Warning: you need to register as a Requester ASAP , and post your tasks to MTurk before Tuesday) http://crowdsourcing-class.org/ Programming the Crowd Crowdsourcing and Human

1.19k views • 104 slides

Enhancing student project selection and allocation in higher education programmes Johann A. Briffa

Enhancing student project selection and allocation in higher education programmes Johann A. Briffa 1 Simon Lygo-Baker 2 26 September 2018 1 Dept. of Comm. & Computer Engineering, University of Malta, Msida MSD 2080, Malta 2 Dept. of Higher

682 views • 35 slides