Search Results for author: Peter J. Ramadge

Found 22 papers, 4 papers with code

ProBF: Learning Probabilistic Safety Certificates with Barrier Functions

1 code implementation22 Dec 2021 Athindran Ramesh Kumar, Sulin Liu, Jaime F. Fisac, Ryan P. Adams, Peter J. Ramadge

In practice, we have inaccurate knowledge of the system dynamics, which can lead to unsafe behaviors due to unmodeled residual dynamics.

Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective

1 code implementation6 Oct 2021 Ting-Han Fan, Peter J. Ramadge

Off-policy Actor-Critic algorithms have demonstrated phenomenal experimental performance but still require better explanations.

DiffLoop: Tuning PID controllers by differentiating through the feedback loop

no code implementations19 Jun 2021 Athindran Ramesh Kumar, Peter J. Ramadge

Since most industrial control applications use PID controllers, PID tuning and anti-windup measures are significant problems.

Task-Agnostic Amortized Inference of Gaussian Process Hyperparameters

1 code implementation NeurIPS 2020 Sulin Liu, Xingyuan Sun, Peter J. Ramadge, Ryan P. Adams

One of the appeals of the GP framework is that the marginal likelihood of the kernel hyperparameters is often available in closed form, enabling optimization and sampling procedures to fit these hyperparameters to data.

Gaussian Processes Model Selection

Projection-Based Constrained Policy Optimization

no code implementations ICLR 2020 Tsung-Yen Yang, Justinian Rosca, Karthik Narasimhan, Peter J. Ramadge

We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs.


A Contraction Approach to Model-based Reinforcement Learning

no code implementations18 Sep 2020 Ting-Han Fan, Peter J. Ramadge

Despite its experimental success, Model-based Reinforcement Learning still lacks a complete theoretical understanding.

Imitation Learning Model-based Reinforcement Learning +1

Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies

no code implementations20 Jun 2020 Tsung-Yen Yang, Justinian Rosca, Karthik Narasimhan, Peter J. Ramadge

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy.

Fairness reinforcement-learning +1

The Landscape of Matrix Factorization Revisited

no code implementations27 Feb 2020 Hossein Valavi, Sulin Liu, Peter J. Ramadge

We show that, in contrast to the general situation, the minimum eigenvalue of strict saddles in $\mathcal{M}_{0}$ is uniformly bounded below zero.

Model Imitation for Model-Based Reinforcement Learning

no code implementations25 Sep 2019 Yueh-Hua Wu, Ting-Han Fan, Peter J. Ramadge, Hao Su

Based on the claim, we propose to learn the transition model by matching the distributions of multi-step rollouts sampled from the transition model and the real ones via WGAN.

Model-based Reinforcement Learning reinforcement-learning

Contact Surface Area: A Novel Signal for Heart Rate Estimation in Smartphone Videos

no code implementations25 Feb 2019 Sara Fridovich-Keil, Peter J. Ramadge

We consider the problem of smartphone video-based heart rate estimation, which typically relies on measuring the green color intensity of the user's skin.

Medical Physics Image and Video Processing

Shared Representational Geometry Across Neural Networks

2 code implementations28 Nov 2018 Qihong Lu, Po-Hsuan Chen, Jonathan W. Pillow, Peter J. Ramadge, Kenneth A. Norman, Uri Hasson

Different neural networks trained on the same dataset often learn similar input-output mappings with very different weights.

A Searchlight Factor Model Approach for Locating Shared Information in Multi-Subject fMRI Analysis

no code implementations29 Sep 2016 Hejia Zhang, Po-Hsuan Chen, Janice Chen, Xia Zhu, Javier S. Turek, Theodore L. Willke, Uri Hasson, Peter J. Ramadge

In this work, we examine a searchlight based shared response model to identify shared information in small contiguous regions (searchlights) across the whole brain.

General Classification

Feedback-Controlled Sequential Lasso Screening

no code implementations21 Aug 2016 Yun Wang, Xu Chen, Peter J. Ramadge

In this context, we propose and explore a feedback controlled sequential screening scheme.

Model Selection

The Symmetry of a Simple Optimization Problem in Lasso Screening

no code implementations21 Aug 2016 Yun Wang, Peter J. Ramadge

Recently dictionary screening has been proposed as an effective way to improve the computational efficiency of solving the lasso problem, which is one of the most commonly used method for learning sparse representations.

A Convolutional Autoencoder for Multi-Subject fMRI Data Aggregation

no code implementations17 Aug 2016 Po-Hsuan Chen, Xia Zhu, Hejia Zhang, Javier S. Turek, Janice Chen, Theodore L. Willke, Uri Hasson, Peter J. Ramadge

We examine two ways to combine the ideas of a factor model and a searchlight based analysis to aggregate multi-subject fMRI data while preserving spatial locality.

Enabling Factor Analysis on Thousand-Subject Neuroimaging Datasets

no code implementations16 Aug 2016 Michael J. Anderson, Mihai Capotă, Javier S. Turek, Xia Zhu, Theodore L. Willke, Yida Wang, Po-Hsuan Chen, Jeremy R. Manning, Peter J. Ramadge, Kenneth A. Norman

The scale of functional magnetic resonance image data is rapidly increasing as large multi-subject datasets are becoming widely available and high-resolution scanners are adopted.

A Reduced-Dimension fMRI Shared Response Model

no code implementations NeurIPS 2015 Po-Hsuan (Cameron) Chen, Janice Chen, Yaara Yeshurun, Uri Hasson, James Haxby, Peter J. Ramadge

Multi-subject fMRI data is critical for evaluating the generality and validity of findings across subjects, and its effective utilization helps improve analysis sensitivity.

Screening Tests for Lasso Problems

no code implementations19 May 2014 Zhen James Xiang, Yun Wang, Peter J. Ramadge

For a given target vector, dictionary screening quickly identifies a subset of dictionary columns that will receive zero weight in a solution of the corresponding lasso problem.

Kernel Hyperalignment

no code implementations NeurIPS 2012 Alexander Lorbert, Peter J. Ramadge

We offer a regularized, kernel extension of the multi-set, orthogonal Procrustes problem, or hyperalignment.

fMRI-Based Inter-Subject Cortical Alignment Using Functional Connectivity

no code implementations NeurIPS 2009 Bryan Conroy, Ben Singer, James Haxby, Peter J. Ramadge

The inter-subject alignment of functional MRI (fMRI) data is important for improving the statistical power of fMRI group analyses.

Boosting with Spatial Regularization

no code implementations NeurIPS 2009 Yongxin Xi, Uri Hasson, Peter J. Ramadge, Zhen J. Xiang

We prove that the proposed algorithm exhibits a ``grouping effect, which encourages the selection of all spatially local, discriminative base classifiers.

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