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

October 10, 2022

Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models
Louis Sharrock, Jack Simons, Song Liu, Mark Beaumont
Generative Model Scientific Inference Bayesian Inference Sequential Neural

October 5, 2022

GAPX: Generalized Autoregressive Paraphrase-Identification X
Yifei Zhou, Renyu Li, Hayden Housen, Ser-Nam Lim
Natural Language Processing Scientific Inference Paraphrase Detection Negative Pair

October 4, 2022

Type theory in human-like learning and inference
Felix A. Sosa, Tomer Ullman
Complex Reasoning Scientific Inference Cognitive Science Scientific Hypothesis Reasoning System

September 25, 2022

WinoDict: Probing language models for in-context word acquisition
Julian Martin Eisenschlos, Jeremy R. Cole, Fangyu Liu, William W. Cohen
Language Model Scientific Inference Coreference Resolution

September 17, 2022

Introspective Learning : A Two-Stage Approach for Inference in Neural Networks
Mohit Prabhushankar, Ghassan AlRegib
Neural Network Scientific Inference Visual Grounding Two Stage Approach

September 9, 2022

ApproxTrain: Fast Simulation of Approximate Multipliers for DNN Training and Inference
Jing Gong, Hassaan Saadat, Hasindu Gamaarachchi, Haris Javaid, Xiaobo Sharon Hu, Sri Parameswaran
Scientific Inference DNN Architecture DNN Training Fast Simulation Inference Accelerator Approximate Multiplier Neural Network Library

September 7, 2022

Inference and Learning for Generative Capsule Models
Alfredo Nazabal, Nikolaos Tsagkas, Christopher K. I. Williams
LeArning Abstract Scientific Inference Expectation Maximization Capsule Network Variational Optimization

September 2, 2022

Inference and dynamic decision-making for deteriorating systems with probabilistic dependencies through Bayesian networks and deep reinforcement learning
Pablo G. Morato, Charalampos P. Andriotis, Konstantinos G. Papakonstantinou, Philippe Rigo
Deep Reinforcement Learning Scientific Inference Policy OpTimization Bayesian Network Global Optimization Observable Markov Decision Process Reinforcement Learning Approach Dynamic Decision Probabilistic Dependency Optimal Execution

August 30, 2022

A Deep Neural Networks ensemble workflow from hyperparameter search to inference leveraging GPU clusters
Pierrick Pochelu, Serge G. Petiton, Bruno Conche
Machine Learning Deep Neural Network Scientific Inference Hyperparameter Optimization Ensemble Method Online autoML GPU Cluster AutoML System Ensemble Post Processing Ensemble Accuracy

August 29, 2022

Inference and Optimization for Engineering and Physical Systems
Mikhail Krechetov
Optimization Purpose Scientific Inference Physical System Bi Level Optimization Position Engineering Ising Model Convex Program Spin Glass Cut Problem

August 26, 2022

Efficient ML Models for Practical Secure Inference
Vinod Ganesan, Anwesh Bhattacharya, Pratyush Kumar, Divya Gupta, Rahul Sharma, Nishanth Chandran
Scientific Inference Secure Inference Efficient Machine Learning FoldFlow 2

August 16, 2022

SOLBP: Second-Order Loopy Belief Propagation for Inference in Uncertain Bayesian Networks
Conrad D. Hougen, Lance M. Kaplan, Magdalena Ivanovska, Federico Cerutti, Kumar Vijay Mishra, Alfred O. Hero
Scientific Inference Bayesian Network Belief Propagation

August 11, 2022

Valid Inference after Causal Discovery
Paula Gradu, Tijana Zrnic, Yixin Wang, Michael I. Jordan
Scientific Inference Causal Inference Causal Discovery Causal Effect Estimation

August 10, 2022

Inaccuracy rates for distributed inference over random networks with applications to social learning
Dragana Bajovic
Financial Application Scientific Inference Social Learning Optimal Rate Random Network Exponential Convergence Rate Large Deviation

August 8, 2022

Deep Computational Model for the Inference of Ventricular Activation Properties
Lei Li, Julia Camps, Abhirup Banerjee, Marcel Beetz, Blanca Rodriguez, Vicente Grau
Scientific Inference Deep Model Patient Specific Cardiac Digital Twin

August 5, 2022

July 23, 2022

Scientific Inference

Papers

Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models

GAPX: Generalized Autoregressive Paraphrase-Identification X

Type theory in human-like learning and inference

WinoDict: Probing language models for in-context word acquisition

Introspective Learning : A Two-Stage Approach for Inference in Neural Networks

ApproxTrain: Fast Simulation of Approximate Multipliers for DNN Training and Inference

Inference and Learning for Generative Capsule Models

Inference and dynamic decision-making for deteriorating systems with probabilistic dependencies through Bayesian networks and deep reinforcement learning

A Deep Neural Networks ensemble workflow from hyperparameter search to inference leveraging GPU clusters

Inference and Optimization for Engineering and Physical Systems

Efficient ML Models for Practical Secure Inference

SOLBP: Second-Order Loopy Belief Propagation for Inference in Uncertain Bayesian Networks

Valid Inference after Causal Discovery

Inaccuracy rates for distributed inference over random networks with applications to social learning

Deep Computational Model for the Inference of Ventricular Activation Properties

Interpretable Uncertainty Quantification in AI for HEP

Motivating explanations in Bayesian networks using MAP-independence

Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference

Defining an action of SO(d)-rotations on images generated by projections of d-dimensional objects: Applications to pose inference with Geometric VAEs

RIBBON: Cost-Effective and QoS-Aware Deep Learning Model Inference using a Diverse Pool of Cloud Computing Instances