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

March 24, 2022

A platform for causal knowledge representation and inference in industrial fault diagnosis based on cubic DUCG
Bu XuSong, Nie Hao, Zhang Zhan, Zhang Qin
Scientific Inference Diverse Platform Causal Knowledge Fault Diagnosis

March 23, 2022

March 22, 2022

Learning from All Vehicles
Dian Chen, Philipp Krähenbühl
LeArning Abstract Scientific Inference Vehicle Plan Ego Vehicle Car Learning to Act Driving Simulator Supervisory Performance

March 20, 2022

Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
Alessandro Barp, Lancelot Da Costa, Guilherme França, Karl Friston, Mark Girolami, Michael I. Jordan, Grigorios A. Pavliotis
Scientific Inference Open Sampling Optimization Process Information Geometry Geometric Approach Geometric Structure Adaptive Agent Geometric Theory Adaptive Decision Making

March 17, 2022

A Learning Framework for Bandwidth-Efficient Distributed Inference in Wireless IoT
Mostafa Hussien, Kim Khoa Nguyen, Mohamed Cheriet
Scientific Inference Internet of Thing Linear Compression Sensor Data Compression Technique Learning Framework

March 16, 2022

March 15, 2022

LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference
Zhongzhi Yu, Yonggan Fu, Shang Wu, Mengquan Li, Haoran You, Yingyan Lin
Neural Network Scientific Inference Fully Connected CRFs Low Precision Training Accurate Training

March 10, 2022

Similarity-based Label Inference Attack against Training and Inference of Split Learning
Junlin Liu, Xinchen Lyu, Qimei Cui, Xiaofeng Tao
Training Data Differential Privacy Scientific Inference Split Learning Label Inference Attack Label Attack Private Label

March 9, 2022

March 7, 2022

Factor Graph-Based Planning as Inference for Autonomous Vehicle Racing
Salman Bari, Xiagong Wang, Ahmad Schoha Haidari, Dirk Wollherr
Scientific Inference Key Factor Autonomous Racing Factor Graph Driving Planning Graph Based Planning Local Planner

March 6, 2022

Compartmental Models for COVID-19 and Control via Policy Interventions
Swapneel Mehta, Noah Kasmanoff
External Control Scientific Inference Covid 19 Modeling Assumption Compartmental Model Probabilistic Programming Language Intervention Policy

March 1, 2022

ArabGend: Gender Analysis and Inference on Arabic Twitter
Hamdy Mubarak, Shammur Absar Chowdhury, Firoj Alam
Scientific Inference Gender Inclusive Text Gender Prediction Arabic Tweet Gender Mobility Gender Gap

February 25, 2022

Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, Luke Zettlemoyer
Large Language Model Context Learning Scientific Inference Integral Role Noisy Demonstration Label Space

February 24, 2022

Estimators of Entropy and Information via Inference in Probabilistic Models
Feras A. Saad, Marco Cusumano-Towner, Vikash K. Mansinghka
Scientific Inference Variational Inference Mutual Information Probabilistic Model Full Information Information Theoretic Linear Estimator Probabilistic Generative Model Stable Entropy

February 23, 2022

Inference of Affordances and Active Motor Control in Simulated Agents
Fedor Scholz, Christian Gumbsch, Sebastian Otte, Martin V. Butz
Scientific Inference Affordance Learning Active Inference Latent State Computational Neuroscience Dynamic Control Sensorimotor Norm Goal Directed Behavior Simulated Agent

February 21, 2022

Online Learning for Orchestration of Inference in Multi-User End-Edge-Cloud Networks
Sina Shahhosseini, Dongjoo Seo, Anil Kanduri, Tianyi Hu, Sung-soo Lim, Bryan Donyanavard, Amir M. Rahmani, Nikil Dutt
Machine Learning Scientific Inference Online Learning Edge Cloud Computation Offloading Co Orchestration Multi User

February 18, 2022

Stochastic Perturbations of Tabular Features for Non-Deterministic Inference with Automunge
Nicholas J. Teague
Scientific Inference Quantum Algorithm Gaussian Noise Noise Injection Random Perturbation Regularization Property Tabular Feature

Scientific Inference

Papers

A platform for causal knowledge representation and inference in industrial fault diagnosis based on cubic DUCG

A Scalable Model Specialization Framework for Training and Inference using Submodels and its Application to Speech Model Personalization

AbductionRules: Training Transformers to Explain Unexpected Inputs

Learning from All Vehicles

Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents

A Learning Framework for Bandwidth-Efficient Distributed Inference in Wireless IoT

AdapLeR: Speeding up Inference by Adaptive Length Reduction

Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation

LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference

Similarity-based Label Inference Attack against Training and Inference of Split Learning

A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices

Data Representativity for Machine Learning and AI Systems

Factor Graph-Based Planning as Inference for Autonomous Vehicle Racing

Compartmental Models for COVID-19 and Control via Policy Interventions

ArabGend: Gender Analysis and Inference on Arabic Twitter

Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

Estimators of Entropy and Information via Inference in Probabilistic Models

Inference of Affordances and Active Motor Control in Simulated Agents

Online Learning for Orchestration of Inference in Multi-User End-Edge-Cloud Networks

Stochastic Perturbations of Tabular Features for Non-Deterministic Inference with Automunge