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

November 27, 2023

PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Deep Neural Network Scientific Inference Multiplier Free Quantization High Performing 1D ConvNet Residual Model Product Quantization Software Evolution Ternary Quantization

November 22, 2023

November 19, 2023

Scale-free networks: improved inference
Nixon Jerez-Lillo, Francisco A. Rodrigues, Pedro L. Ramos
Scientific Inference Bayesian Inference Continuous Network Power Law Degree Distribution Exact Posterior

November 15, 2023

Aligning Neural Machine Translation Models: Human Feedback in Training and Inference
Miguel Moura Ramos, Patrick Fernandes, António Farinhas, André F. T. Martins
Language Model Reinforcement Learning Training Data Machine Translation Scientific Inference Human Feedback Reward Model Neural Machine Translation Model

November 13, 2023

Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval
Junyang Chen, Hanjiang Lai
Vision Language Model Scientific Inference Pre Training MAESTRO Dataset Image Text Pair Hyper Tune Composed Image Retrieval Pre Trained Vision

November 12, 2023

Inference and Interference: The Role of Clipping, Pruning and Loss Landscapes in Differentially Private Stochastic Gradient Descent
Lauren Watson, Eric Gan, Mohan Dantam, Baharan Mirzasoleiman, Rik Sarkar
Neural Network Gradient Descent Stochastic Gradient Descent Scientific Inference Edge Pruning Loss Landscape Private Stochastic Private Stochastic Gradient Descent High Dimensional Clipping

November 9, 2023

November 7, 2023

November 2, 2023

PPI++: Efficient Prediction-Powered Inference
Anastasios N. Angelopoulos, John C. Duchi, Tijana Zrnic
Machine Learning Scientific Inference Estimation Task Predictive Inference Confidence Set

November 1, 2023

Inference of CO2 flow patterns -- a feasibility study
Abhinav Prakash Gahlot, Huseyin Tuna Erdinc, Rafael Orozco, Ziyi Yin, Felix J. Herrmann
Scientific Inference Feasibility Study Gas Plume Time Lapse Seismic

October 27, 2023

MOSEL: Inference Serving Using Dynamic Modality Selection
Bodun Hu, Le Xu, Jeongyoon Moon, Neeraja J. Yadwadkar, Aditya Akella
Scientific Inference Input Modality Inference Service Modality Selection Multi Modal Machine Learning Modality Compensation

October 23, 2023

October 19, 2023

Contrastive Learning for Inference in Dialogue
Etsuko Ishii, Yan Xu, Bryan Wilie, Ziwei Ji, Holy Lovenia, Willy Chung, Pascale Fung
Contrastive Learning Scientific Inference Dialogue Utterance Inference Task Inductive Reasoning Semantic Gap Inductive Inference Inference Scheme

October 17, 2023

Context-Aware Meta-Learning
Christopher Fifty, Dennis Duan, Ronald G. Junkins, Ehsan Amid, Jure Leskovec, Christopher Re, Sebastian Thrun
Scientific Inference Meta Learning Meta Training Meta Learning Benchmark

October 13, 2023

Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN
Florence Regol, Joud Chataoui, Mark Coates
Scientific Inference Gating Mechanism Early Exit Dynamic Neural Network Inference Module

October 12, 2023

Large Language Models for Scientific Synthesis, Inference and Explanation
Yizhen Zheng, Huan Yee Koh, Jiaxin Ju, Anh T. N. Nguyen, Lauren T. May, Geoffrey I. Webb, Shirui Pan
Large Language Model Line by Line Explanation Scientific Inference Scientific Synthesis

Scientific Inference

Papers

PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions

Input Compression with Positional Consistency for Efficient Training and Inference of Transformer Neural Networks

Accelerating Inference in Molecular Diffusion Models with Latent Representations of Protein Structure

Scale-free networks: improved inference

Aligning Neural Machine Translation Models: Human Feedback in Training and Inference

Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval

Inference and Interference: The Role of Clipping, Pruning and Loss Landscapes in Differentially Private Stochastic Gradient Descent

Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiency

Inference for Probabilistic Dependency Graphs

Kernel-, mean- and noise-marginalised Gaussian processes for exoplanet transits and $H_0$ inference

Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models

PPI++: Efficient Prediction-Powered Inference

Inference of CO2 flow patterns -- a feasibility study

MOSEL: Inference Serving Using Dynamic Modality Selection

Externally Valid Policy Evaluation Combining Trial and Observational Data

CAD-DA: Controllable Anomaly Detection after Domain Adaptation by Statistical Inference

Contrastive Learning for Inference in Dialogue

Context-Aware Meta-Learning

Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN

Large Language Models for Scientific Synthesis, Inference and Explanation