100 citations · 197 across the 23 of their papers we have counts for
23 papers
Fast, Smooth, and Safe: Implicit Control Barrier Functions through Reach-Avoid Differential Dynamic Programming
Athindran Ramesh Kumar, Kai-Chieh Hsu, Peter J. Ramadge +1
Safety is a central requirement for autonomous system operation across domains. Hamilton-Jacobi (HJ) reachability analysis can be used to construct "least-restrictive" safety filte…
Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings
Ta-Chung Chi, Ting-Han Fan, Li-Wei Chen +2
The use of positional embeddings in transformer language models is widely accepted. However, recent research has called into question the necessity of such embeddings. We further e…
Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation
Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky +1
Unlike recurrent models, conventional wisdom has it that Transformers cannot perfectly model regular languages. Inspired by the notion of working memory, we propose a new Transform…
Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis
Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky +1
Length extrapolation permits training a transformer language model on short sequences that preserves perplexities when tested on substantially longer sequences. A relative position…
Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
Ting-Han Fan, Ta-Chung Chi, Alexander I. Rudnicky +1
While deep generative models have succeeded in image processing, natural language processing, and reinforcement learning, training that involves discrete random variables remains c…
KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation
Ta-Chung Chi, Ting-Han Fan, Peter J. Ramadge +1
Relative positional embeddings (RPE) have received considerable attention since RPEs effectively model the relative distance among tokens and enable length extrapolation. We propos…
ProBF: Learning Probabilistic Safety Certificates with Barrier Functions
Athindran Ramesh Kumar, Sulin Liu, Jaime F. Fisac +2
Safety-critical applications require controllers/policies that can guarantee safety with high confidence. The control barrier function is a useful tool to guarantee safety if we ha…
Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective
Ting-Han Fan, Peter J. Ramadge
Off-policy Actor-Critic algorithms have demonstrated phenomenal experimental performance but still require better explanations. To this end, we show its policy evaluation error on…
DiffLoop: Tuning PID controllers by differentiating through the feedback loop
Athindran Ramesh Kumar, Peter J. Ramadge
Since most industrial control applications use PID controllers, PID tuning and anti-windup measures are significant problems. This paper investigates tuning the feedback gains of a…
Safe Reinforcement Learning with Natural Language Constraints
Tsung-Yen Yang, Michael Hu, Yinlam Chow +2
While safe reinforcement learning (RL) holds great promise for many practical applications like robotics or autonomous cars, current approaches require specifying constraints in ma…
A Contraction Approach to Model-based Reinforcement Learning
Ting-Han Fan, Peter J. Ramadge
Despite its experimental success, Model-based Reinforcement Learning still lacks a complete theoretical understanding. To this end, we analyze the error in the cumulative reward us…
Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies
Tsung-Yen Yang, Justinian Rosca, Karthik Narasimhan +1
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. The baseline policy c…
The Landscape of Matrix Factorization Revisited
Hossein Valavi, Sulin Liu, Peter J. Ramadge
We revisit the landscape of the simple matrix factorization problem. For low-rank matrix factorization, prior work has shown that there exist infinitely many critical points all of…
Model Imitation for Model-Based Reinforcement Learning
Yueh-Hua Wu, Ting-Han Fan, Peter J. Ramadge +1
Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. However, due to estimation error, rollout…
Contact Surface Area: A Novel Signal for Heart Rate Estimation in Smartphone Videos
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. We describe a novel signa…
Shared Representational Geometry Across Neural Networks
Qihong Lu, Po-Hsuan Chen, Jonathan W. Pillow +3
Different neural networks trained on the same dataset often learn similar input-output mappings with very different weights. Is there some correspondence between these neural netwo…
Mapping Between fMRI Responses to Movies and their Natural Language Annotations
Kiran Vodrahalli, Po-Hsuan Chen, Yingyu Liang +8
Several research groups have shown how to correlate fMRI responses to the meanings of presented stimuli. This paper presents new methods for doing so when only a natural language a…
A Searchlight Factor Model Approach for Locating Shared Information in Multi-Subject fMRI Analysis
Hejia Zhang, Po-Hsuan Chen, Janice Chen +5
There is a growing interest in joint multi-subject fMRI analysis. The challenge of such analysis comes from inherent anatomical and functional variability across subjects. One appr…
The Symmetry of a Simple Optimization Problem in Lasso Screening
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 met…
Feedback-Controlled Sequential Lasso Screening
Yun Wang, Xu Chen, Peter J. Ramadge
One way to solve lasso problems when the dictionary does not fit into available memory is to first screen the dictionary to remove unneeded features. Prior research has shown that…
A Convolutional Autoencoder for Multi-Subject fMRI Data Aggregation
Po-Hsuan Chen, Xia Zhu, Hejia Zhang +5
Finding the most effective way to aggregate multi-subject fMRI data is a long-standing and challenging problem. It is of increasing interest in contemporary fMRI studies of human c…
Screening Tests for Lasso Problems
Zhen James Xiang, Yun Wang, Peter J. Ramadge
This paper is a survey of dictionary screening for the lasso problem. The lasso problem seeks a sparse linear combination of the columns of a dictionary to best match a given targe…
A Bayesian Boosting Model
Alexander Lorbert, David M. Blei, Robert E. Schapire +1
We offer a novel view of AdaBoost in a statistical setting. We propose a Bayesian model for binary classification in which label noise is modeled hierarchically. Using variational…