High Dimensional

High-dimensional data analysis focuses on extracting meaningful information and building predictive models from datasets with numerous variables, often exceeding the number of observations. Current research emphasizes developing computationally efficient algorithms, such as stochastic gradient descent and its variants, and novel model architectures like graph neural networks and deep learning approaches tailored to handle the unique challenges posed by high dimensionality, including issues of sparsity and missing data. These advancements are crucial for addressing complex problems across diverse fields, including scientific modeling, robotics, and financial risk assessment, where high-dimensional data are increasingly prevalent.

Papers

December 23, 2021

Generalization Error Bounds on Deep Learning with Markov Datasets
Lan V. Truong
Deep Learning High Dimensional Generalization Error Generalization Error Bound Learning Probabilistic Symmetrization

December 21, 2021

Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding
Chloe He, Borja G. Leon, Francesco Belardinelli
Reinforcement Learning Deep Reinforcement Learning High Dimensional Tiny Machine Learning Model Based Shielding Android Robot Wildlife Fence

December 16, 2021

High-Dimensional Inference in Bayesian Networks
Fritz M. Bayer, Giusi Moffa, Niko Beerenwinkel, Jack Kuipers
High Dimensional Scientific Inference Bayesian Network Categorical Data Approximate Inference Marginal Distribution

December 14, 2021

Stochastic Actor-Executor-Critic for Image-to-Image Translation
Ziwei Luo, Jing Hu, Xin Wang, Siwei Lyu, Bin Kong, Youbing Yin, Qi Song, Xi Wu
High Dimensional Image to Image Translation Stochastic Way Model Free Deep Reinforcement Learning Latent Action Policy Actor Critic

December 13, 2021

Fast Single-Core K-Nearest Neighbor Graph Computation
Dan Kluser, Jonas Bokstaller, Samuel Rutz, Tobias Buner
High Dimensional Distance Metric Nearest Neighbor Graph Low Dimensional Data Single Core

December 9, 2021

High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning
Uta Pigorsch, Sebastian Schäfer
Deep Reinforcement Learning High Dimensional Deep Q Learning Portfolio Management

December 3, 2021

Provably Valid and Diverse Mutations of Real-World Media Data for DNN Testing
Yuanyuan Yuan, Qi Pang, Shuai Wang
High Dimensional Video Dataset Concurrent Validity Single Point Mutation DNN Testing

December 2, 2021

Level set learning with pseudo-reversible neural networks for nonlinear dimension reduction in function approximation
Yuankai Teng, Zhu Wang, Lili Ju, Anthony Gruber, Guannan Zhang
Neural Network High Dimensional Dimensionality Reduction Function Approximation Different Level Dimensional Input Active Subspace

November 27, 2021

A Two-Stage Feature Selection Approach for Robust Evaluation of Treatment Effects in High-Dimensional Observational Data
Md Saiful Islam, Sahil Shikalgar, Md. Noor-E-Alam
High Dimensional Causal Inference Feature Selection Treatment Effect Robust Evaluation Randomized Controlled Trial Elastic Net Robust Causal

November 21, 2021

November 17, 2021

Universal Inference Meets Random Projections: A Scalable Test for Log-concavity
Robin Dunn, Aditya Gangrade, Larry Wasserman, Aaditya Ramdas
High Dimensional Maximum Likelihood Random Projection Test Bed Inference Framework Log Concave Log Concavity

November 13, 2021

November 12, 2021

High Dimensional

Papers

Generalization Error Bounds on Deep Learning with Markov Datasets

Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding

High-Dimensional Inference in Bayesian Networks

Stochastic Actor-Executor-Critic for Image-to-Image Translation

Fast Single-Core K-Nearest Neighbor Graph Computation

High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning

Provably Valid and Diverse Mutations of Real-World Media Data for DNN Testing

Level set learning with pseudo-reversible neural networks for nonlinear dimension reduction in function approximation

Optimizing High-Dimensional Physics Simulations via Composite Bayesian Optimization

Encoding Causal Macrovariables

Graph Embedding via High Dimensional Model Representation for Hyperspectral Images

On the rate of convergence of a classifier based on a Transformer encoder

A Two-Stage Feature Selection Approach for Robust Evaluation of Treatment Effects in High-Dimensional Observational Data

A Data-Driven Line Search Rule for Support Recovery in High-dimensional Data Analysis

Deep Probability Estimation

Universal Inference Meets Random Projections: A Scalable Test for Log-concavity

The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods

Efficient Binary Embedding of Categorical Data using BinSketch

Dynamic treatment effects: high-dimensional inference under model misspecification

Differential privacy and robust statistics in high dimensions