Scientific Inference

Scientific inference, the process of drawing conclusions from data, is a core challenge across numerous scientific fields, with current research focusing on improving efficiency and accuracy. This involves developing novel algorithms and architectures, such as those based on Bayesian networks, diffusion transformers, and autoregressive models, to optimize inference processes in various contexts, including large language models and image processing. These advancements are crucial for accelerating scientific discovery and enabling real-world applications in areas like personalized medicine, legal tech, and industrial automation, where efficient and reliable inference is paramount. The emphasis is on addressing computational bottlenecks and improving the reliability of inferences, particularly in scenarios with limited data or complex models.

Papers

July 22, 2022

Inference skipping for more efficient real-time speech enhancement with parallel RNNs
Xiaohuai Le, Tong Lei, Kai Chen, Jing Lu
Neural Network Scientific Inference Speech Enhancement Speech Enhancement Model

July 21, 2022

July 18, 2022

Robust Simulation-Based Inference in Cosmology with Bayesian Neural Networks
Pablo Lemos, Miles Cranmer, Muntazir Abidi, ChangHoon Hahn, Michael Eickenberg, Elena Massara, David Yallup, Shirley Ho
Scientific Inference Robust Version Bayesian Neural Network Astronomical Data Simulation Based Inference Exact Inference Redshift Survey

July 17, 2022

Nonmyopic Distilled Data Association Belief Space Planning Under Budget Constraints
Moshe Shienman, Vadim Indelman
Scientific Inference Autonomous Agent Budget Constraint Belief Space Planning

July 13, 2022

Entry-Flipped Transformer for Inference and Prediction of Participant Behavior
Bo Hu, Tat-Jen Cham
Transformer Based Human Prediction Scientific Inference Spatio Temporal Pedestrian Data Participant State Per Frame

July 12, 2022

Look-ups are not (yet) all you need for deep learning inference
Calvin McCarter, Nicholas Dronen
Neural Network Scientific Inference Matrix Multiplication Lookup Table Neural Network Inference Deep Learning Inference

June 25, 2022

Multi-Variate Time Series Forecasting on Variable Subsets
Jatin Chauhan, Aravindan Raghuveer, Rishi Saket, Jay Nandy, Balaraman Ravindran
Scientific Inference Time Series Forecasting Multivariate Time Series Forecasting Forecasting Model Inference Task High Quality Subset

June 24, 2022

Signal Knowledge Graph
Anj Simmons, Rajesh Vasa
Knowledge Graph Scientific Inference Reasoning System

June 23, 2022

Indecision Trees: Learning Argument-Based Reasoning under Quantified Uncertainty
Jonathan S. Kent, David H. Menager
Complex Reasoning Scientific Inference Decision Tree Machine Learning System Reasoning System Quantified Uncertainty

June 21, 2022

SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding
Hermann Blum, Marcus G. Müller, Abel Gawel, Roland Siegwart, Cesar Cadena
Scientific Inference Area MaPPing Semantic Segmentation Model Object Discovery Self Supervised Signal Semantic Class Semantic Perception

June 20, 2022

Deep Random Vortex Method for Simulation and Inference of Navier-Stokes Equations
Rui Zhang, Peiyan Hu, Qi Meng, Yue Wang, Rongchan Zhu, Bingguang Chen, Zhi-Ming Ma, Tie-Yan Liu
Scientific Inference Simulation Study Navier Stokes Random Vortex

June 15, 2022

Theory of Machine Learning with Limited Data
Marina Sapir
Machine Learning Scientific Inference Theoretical Understanding Limited Data Statistical Learning Theory Contrastive Meta Abduction Method

June 13, 2022

SIXO: Smoothing Inference with Twisted Objectives
Dieterich Lawson, Allan Raventós, Andrew Warrington, Scott Linderman
Scientific Inference Posterior Approximation Model Learning Sequential Monte Carlo Inference Algorithm

June 11, 2022

June 9, 2022

Discriminative and Generative Learning for Linear Estimation of Random Signals [Lecture Notes]
Nir Shlezinger, Tirza Routtenberg
Scientific Inference Generative Learning Discriminative Model Discriminative Reply Lecture Note Bayesian Signal Random Telegraph Signal

June 4, 2022

Beyond Value: CHECKLIST for Testing Inferences in Planning-Based RL
Kin-Ho Lam, Delyar Tabatabai, Jed Irvine, Donald Bertucci, Anita Ruangrotsakun, Minsuk Kahng, Alan Fern
Reinforcement Learning Scientific Inference Net Present Value Inference Problem Assessment Checklist Real Time Strategy

June 1, 2022

A Theoretical Framework for Inference Learning
Nick Alonso, Beren Millidge, Jeff Krichmar, Emre Neftci
Scientific Inference Back Propagation Machine Learning Inference Theoretical Framework

May 31, 2022

Simulator-Based Inference with Waldo: Confidence Regions by Leveraging Prediction Algorithms and Posterior Estimators for Inverse Problems
Luca Masserano, Tommaso Dorigo, Rafael Izbicki, Mikael Kuusela, Ann B. Lee
Scientific Inference Inverse Problem Posterior Inference Parameter Inference Predictive Algorithm Neural Density Confidence Region

Scientific Inference

Papers

Inference skipping for more efficient real-time speech enhancement with parallel RNNs

Inference of Regulatory Networks Through Temporally Sparse Data

A Theoretical Framework for Inference and Learning in Predictive Coding Networks

Robust Simulation-Based Inference in Cosmology with Bayesian Neural Networks

Nonmyopic Distilled Data Association Belief Space Planning Under Budget Constraints

Entry-Flipped Transformer for Inference and Prediction of Participant Behavior

Look-ups are not (yet) all you need for deep learning inference

Multi-Variate Time Series Forecasting on Variable Subsets

Signal Knowledge Graph

Indecision Trees: Learning Argument-Based Reasoning under Quantified Uncertainty

SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding

Deep Random Vortex Method for Simulation and Inference of Navier-Stokes Equations

Theory of Machine Learning with Limited Data

SIXO: Smoothing Inference with Twisted Objectives

Bridging the Gap Between Training and Inference of Bayesian Controllable Language Models

Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena

Discriminative and Generative Learning for Linear Estimation of Random Signals [Lecture Notes]

Beyond Value: CHECKLIST for Testing Inferences in Planning-Based RL

A Theoretical Framework for Inference Learning

Simulator-Based Inference with Waldo: Confidence Regions by Leveraging Prediction Algorithms and Posterior Estimators for Inverse Problems