Search Results for author:
Found 28 papers, 7 papers with code
Generative Marginalization Models
We introduce marginalization models (MaMs), a new family of generative models for high-dimensional discrete data.
Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings
The use of positional embeddings in transformer language models is widely accepted.
Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation
Unlike recurrent models, conventional wisdom has it that Transformers cannot perfectly model regular languages.
Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis
Length extrapolation permits training a transformer language model on short sequences that preserves perplexities when tested on substantially longer sequences.
Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
While deep generative models have succeeded in image processing, natural language processing, and reinforcement learning, training that involves discrete random variables remains challenging due to the high variance of its gradient estimation process.
KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation
Relative positional embeddings (RPE) have received considerable attention since RPEs effectively model the relative distance among tokens and enable length extrapolation.
ProBF: Learning Probabilistic Safety Certificates with Barrier Functions
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
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
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
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.
Safe Reinforcement Learning with Natural Language Constraints
We then develop an agent with a modular architecture that can interpret and adhere to such textual constraints while learning new tasks.
Projection-Based Constrained Policy Optimization
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
Despite its experimental success, Model-based Reinforcement Learning still lacks a complete theoretical understanding.
Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies
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 Landscape of Matrix Factorization Revisited
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
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
+1
Contact Surface Area: A Novel Signal for Heart Rate Estimation in Smartphone Videos
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
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
In this work, we examine a searchlight based shared response model to identify shared information in small contiguous regions (searchlights) across the whole brain.
The Symmetry of a Simple Optimization Problem in Lasso Screening
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.
Feedback-Controlled Sequential Lasso Screening
In this context, we propose and explore a feedback controlled sequential screening scheme.
A Convolutional Autoencoder for Multi-Subject fMRI Data Aggregation
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
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
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
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
We offer a regularized, kernel extension of the multi-set, orthogonal Procrustes problem, or hyperalignment.
Boosting with Spatial Regularization
We prove that the proposed algorithm exhibits a ``grouping effect, which encourages the selection of all spatially local, discriminative base classifiers.
fMRI-Based Inter-Subject Cortical Alignment Using Functional Connectivity
The inter-subject alignment of functional MRI (fMRI) data is important for improving the statistical power of fMRI group analyses.
