Machine Learning Inference

Machine learning inference focuses on efficiently and reliably using trained models to make predictions or solve tasks with new data. Current research emphasizes improving the trustworthiness and efficiency of inference, exploring diverse model architectures like probabilistic circuits, predictive coding networks, and ordinary differential equations, as well as optimizing inference for resource-constrained environments (e.g., edge devices, microcontrollers). These advancements are crucial for enhancing the reliability and applicability of machine learning across various domains, from medical diagnosis and industrial control to astrophysics and autonomous systems, while addressing concerns about energy efficiency, privacy, and explainability.

Papers

July 8, 2024

Fostering Trust and Quantifying Value of AI and ML
Dalmo Cirne, Veena Calambur
Machine Learning Artificial Intelligence Building Trust Trustworthy Machine Learning Machine Learning Inference Value Estimation

July 4, 2024

Predictive Coding Networks and Inference Learning: Tutorial and Survey
Björn van Zwol, Ro Jefferson, Egon L. van den Broek
Timely Survey Tutorial Review Neural Activity Predictive Coding Neuroscience Research Machine Learning Inference

June 2, 2024

VeriSplit: Secure and Practical Offloading of Machine Learning Inferences across IoT Devices
Han Zhang, Zifan Wang, Mihir Dhamankar, Matt Fredrikson, Yuvraj Agarwal
Computation Method Hardware Accelerator Internet of Thing Device Task Offloading Secure Approach Machine Learning Inference Cloud Resource Model Confidentiality

May 29, 2024

HawkVision: Low-Latency Modeless Edge AI Serving
ChonLam Lao, Jiaqi Gao, Ganesh Ananthanarayanan, Aditya Akella, Minlan Yu
Model Inference Machine Learning Inference Model Latency

March 21, 2024

Soft Learning Probabilistic Circuits
Soroush Ghandi, Benjamin Quost, Cassio de Campos
Probabilistic Circuit Machine Learning Inference Tractable Probabilistic Model Greedy Learning

March 16, 2024

ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference
Krzysztof Kacprzyk, Samuel Holt, Jeroen Berrevoets, Zhaozhi Qian, Mihaela van der Schaar
Treatment Effect Machine Learning Inference Differential Equation Discovery

February 12, 2024

Identifying architectural design decisions for achieving green ML serving
Francisco Durán, Silverio Martínez-Fernández, Matias Martinez, Patricia Lago
Machine Learning Model Machine Learning Inference Green AI

February 6, 2024

LtU-ILI: An All-in-One Framework for Implicit Inference in Astrophysics and Cosmology
Matthew Ho, Deaglan J. Bartlett, Nicolas Chartier, Carolina Cuesta-Lazaro, Simon Ding, Axel Lapel, Pablo Lemos, Christopher C. Lovell, T. Lucas Makinen, Chirag Modi, Viraj Pandya, Shivam Pandey, Lucia A. Perez, Benjamin Wandelt, Greg L. Bryan
New Framework Scientific Inference Astronomical Data Machine Learning Inference

December 21, 2023

Structure-Aware Path Inference for Neural Finite State Transducers
Weiting Tan, Chu-cheng Lin, Jason Eisner
Machine Learning Inference Finite State Transducer Neurosymbolic Framework Multi Path Latent Space Alignment

December 4, 2023

FeaInfNet: Diagnosis in Medical Image with Feature-Driven Inference and Visual Explanations
Yitao Peng, Lianghua He, Die Hu, Yihang Liu, Longzhen Yang, Shaohua Shang
Inherent Interpretability Medical Image Medical Diagnosis Visual Explanation Interpretable Deep Learning Machine Learning Inference Driven Inference

October 24, 2023

Amortised Inference in Neural Networks for Small-Scale Probabilistic Meta-Learning
Matthew Ashman, Tommy Rochussen, Adrian Weller
Neural Network Meta Learning Bayesian Inference Task Specific Machine Learning Inference Variational Approximation Amortised Inference

October 7, 2023

Automatic and Efficient Customization of Neural Networks for ML Applications
Yuhan Liu, Chengcheng Wan, Kuntai Du, Henry Hoffmann, Junchen Jiang, Shan Lu, Michael Maire
Neural Network Machine Learning Application Machine Learning Inference Real Time Customization Multi Loss Commercial ML

September 27, 2023

LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints
Weidi Xu, Jingwei Wang, Lele Xie, Jianshan He, Hongting Zhou, Taifeng Wang, Xiaopei Wan, Jingdong Chen, Chao Qu, Wei Chu
Mean Field Neuro Symbolic Approach Machine Learning Inference Logical Constraint Logic Lm

June 8, 2023

Energy-efficient Wearable-to-Mobile Offload of ML Inference for PPG-based Heart-Rate Estimation
Alessio Burrello, Matteo Risso, Noemi Tomasello, Yukai Chen, Luca Benini, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari
PPG Signal Heart Rate Smartwatch Payment Machine Learning Inference

June 1, 2023

Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference
Yan Xu, Deqian Kong, Dehong Xu, Ziwei Ji, Bo Pang, Pascale Fung, Ying Nian Wu
Response Generation Dialogue Datasets Machine Learning Inference Knowledge Grounded Dialogue Generation

May 30, 2023

Towards Machine Learning and Inference for Resource-constrained MCUs
Yushan Huang, Hamed Haddadi
Machine Learning Machine Learning Model Scientific Inference Machine Learning Inference Inference Accelerator Fish Segmentation

April 3, 2023

Online Algorithms for Hierarchical Inference in Deep Learning applications at the Edge
Vishnu Narayanan Moothedath, Jaya Prakash Champati, James Gross
Machine Learning Model Extreme Edge Edge Device Online Algorithm Deep Learning Application Tiny Machine Learning Machine Learning Inference Hierarchical Inference

December 25, 2022

Quality at the Tail of Machine Learning Inference
Zhengxin Yang, Wanling Gao, Chunjie Luo, Lei Wang, Fei Tang, Xu Wen, Jianfeng Zhan
Quality Issue Inference Time Exact Inference Machine Learning Inference Real Time Inference Thin Tail

November 21, 2022

Implicit Training of Energy Model for Structure Prediction
Shiv Shankar, Vihari Piratla
Deep Learning Loss Landscape Structure Prediction Machine Learning Inference Energy Modeling Dynamic Loss Implicit Learning

October 29, 2022

MinUn: Accurate ML Inference on Microcontrollers
Shikhar Jaiswal, Rahul Kiran Kranti Goli, Aayan Kumar, Vivek Seshadri, Rahul Sharma
TinyML Model Inference Framework 32 Bit Microcontrollers Machine Learning Inference