Bayesian Perspective

Bayesian perspectives are increasingly applied to address challenges in machine learning, particularly concerning uncertainty quantification and robust model performance. Current research focuses on developing probabilistic evaluation frameworks for large language models and other deep learning architectures, employing Bayesian methods like Gaussian processes, Bayesian neural networks, and variational inference to improve model reliability and interpretability. This shift towards probabilistic approaches is significant because it allows for more nuanced assessments of model capabilities, leading to improved decision-making in high-stakes applications such as drug discovery, autonomous navigation, and medical image analysis. The resulting advancements enhance the trustworthiness and generalizability of machine learning models across diverse domains.

Papers

July 30, 2024

Non-Bayesian Social Learning with Multiview Observations
Dongyan Sui, Weichen Cao, Stefan Vlaski, Chun Guan, Siyang Leng
Bayesian Perspective Social Learning Multiview Observation

July 27, 2024

Bayesian meta learning for trustworthy uncertainty quantification
Zhenyuan Yuan, Thinh T. Doan
Meta Learning Bayesian Perspective Trust Inference Bayesian Regression Meta Learning Prior

July 9, 2024

Simple and Interpretable Probabilistic Classifiers for Knowledge Graphs
Christian Riefolo, Nicola Fanizzi, Claudia d'Amato
Knowledge Graph Bayesian Perspective Description Logic Interpretable Classifier Probabilistic Classifier Naive Bayes Classifier

June 26, 2024

B-TMS: Bayesian Traversable Terrain Modeling and Segmentation Across 3D LiDAR Scans and Maps for Enhanced Off-Road Navigation
Minho Oh, Gunhee Shin, Seoyeon Jang, Seungjae Lee, Dongkyu Lee, Wonho Song, Byeongho Yu, Hyungtae Lim, Jaeyoung Lee, Hyun Myung
Local Navigation Bayesian Perspective Point Cloud Data Road Environment LiDAR Segmentation Digital Map Segmentation Algorithm Terrain Model

June 24, 2024

Peirce in the Machine: How Mixture of Experts Models Perform Hypothesis Construction
Bruce Rushing
New Machine Mixture Component Bayesian Perspective Bayesian Approach Expert Model Abductive Reasoning Hypothesis Generation

June 11, 2024

Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis
Zeinab Abboud, Herve Lombaert, Samuel Kadoury
Uncertainty Quantification Medical Image Analysis Bayesian Neural Network Bayesian Perspective Predictive Uncertainty Posterior Approximation Bayesian Neural

June 8, 2024

Bayesian vs. PAC-Bayesian Deep Neural Network Ensembles
Nick Hauptvogel, Christian Igel
Bayesian Neural Network Deep Ensemble Bayesian Perspective PAC Bayesian Bayesian Ensemble

June 7, 2024

Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning
Roman Belaire, Arunesh Sinha, Pradeep Varakantham
Adversarial Attack Deep Reinforcement Learning Adversarial Perturbation Bayesian Perspective Adversarial Noise Adversarial Reinforcement Learning Error Minimizing Noise

June 6, 2024

Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models
Ding Huang, Ting Li, Jian Huang
Diffusion Model Domain Adaptation Pre Trained Model Bayesian Perspective Effective Approach Large Diffusion Model Multi Property Steering

May 31, 2024

Scalable Bayesian Learning with posteriors
Samuel Duffield, Kaelan Donatella, Johnathan Chiu, Phoebe Klett, Daniel Simpson
Posterior Inference Bayesian Perspective Posterior Approximation Posterior Mode Scalable Bayesian

May 28, 2024

Evaluating Bayesian deep learning for radio galaxy classification
Devina Mohan, Anna M. M. Scaife
Bayesian Neural Network Bayesian Perspective Uncertainty Calibration Calibrated Uncertainty Radio Astronomy Radio Galaxy Classification

May 27, 2024

Towards One Model for Classical Dimensionality Reduction: A Probabilistic Perspective on UMAP and t-SNE
Aditya Ravuri, Neil D. Lawrence
Full Model Dimensionality Reduction Bayesian Perspective Theoretical Analysis MAP Estimation

May 9, 2024

Bayesian Prediction-Powered Inference
R. Alex Hofer, Joshua Maynez, Bhuwan Dhingra, Adam Fisch, Amir Globerson, William W. Cohen
Scientific Inference Bayesian Inference Bayesian Perspective Predictive Inference Human Labeled

May 3, 2024

May 2, 2024

Accelerating Convergence in Bayesian Few-Shot Classification
Tianjun Ke, Haoqun Cao, Feng Zhou
Classification Code Shot Learning Variational Inference Early Stage Convergence Shot Classification Bayesian Perspective

April 24, 2024

Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic Perspective
Vaisakh Shaj
State Space Model World Model Bayesian Perspective Novel Bayesian Temporal Abstraction Bayesian Brain

March 24, 2024

Partially Blinded Unlearning: Class Unlearning for Deep Networks a Bayesian Perspective
Subhodip Panda, Shashwat Sourav, Prathosh A. P
Deep Network Machine Unlearning Bayesian Perspective Unlearned Model Knowledge Unlearning Surface Regularization Class Unlearning

March 19, 2024

Detection of Malicious Agents in Social Learning
Valentina Shumovskaia, Mert Kayaalp, Ali H. Sayed
Data Detection Bayesian Perspective Hypothesis Testing Malicious Agent Social Learning Heterogeneous Model

March 2, 2024

Can a Confident Prior Replace a Cold Posterior?
Martin Marek, Brooks Paige, Pavel Izmailov
Bayesian Neural Network Bayesian Perspective Prior Distribution Prior Model Cold Posterior

Bayesian Perspective

Papers

Non-Bayesian Social Learning with Multiview Observations

Bayesian meta learning for trustworthy uncertainty quantification

Simple and Interpretable Probabilistic Classifiers for Knowledge Graphs

B-TMS: Bayesian Traversable Terrain Modeling and Segmentation Across 3D LiDAR Scans and Maps for Enhanced Off-Road Navigation

Peirce in the Machine: How Mixture of Experts Models Perform Hypothesis Construction

Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis

Bayesian vs. PAC-Bayesian Deep Neural Network Ensembles

Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning

Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models

Scalable Bayesian Learning with posteriors

Evaluating Bayesian deep learning for radio galaxy classification

Towards One Model for Classical Dimensionality Reduction: A Probabilistic Perspective on UMAP and t-SNE

Bayesian Prediction-Powered Inference

A comparative study of conformal prediction methods for valid uncertainty quantification in machine learning

Bayesian and Convolutional Networks for Hierarchical Morphological Classification of Galaxies

Accelerating Convergence in Bayesian Few-Shot Classification

Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic Perspective

Partially Blinded Unlearning: Class Unlearning for Deep Networks a Bayesian Perspective

Detection of Malicious Agents in Social Learning

Can a Confident Prior Replace a Cold Posterior?