Model Learning

Model learning focuses on developing algorithms and architectures that enable efficient and accurate learning from data, aiming to improve model performance and generalization. Current research emphasizes improving data efficiency through techniques like masked data consistency, class-wise hardness modeling, and data selection based on information compression principles, often employing neural networks, including graph neural networks and variational autoencoders. These advancements are crucial for various applications, such as video segmentation, natural language understanding, robotics control, and communication systems optimization, by enhancing model accuracy, robustness, and interpretability. The ultimate goal is to create more reliable and efficient models across diverse domains.

Papers

September 14, 2023

Uncertainty quantification for learned ISTA
Frederik Hoppe, Claudio Mayrink Verdun, Felix Krahmer, Hannah Laus, Holger Rauhut
Uncertainty Quantification Inverse Problem Linear Estimator Model Learning

August 28, 2023

Model-based learning for location-to-channel mapping
Baptiste Chatelier, Luc Le Magoarou, Vincent Corlay, Matthieu Crussière
Channel Estimation Model Learning Classical Neural Network Spectral Bias Frequency Function Channel Knowledge

May 16, 2023

On Dataset Transferability in Active Learning for Transformers
Fran Jelenić, Josip Jukić, Nina Drobac, Jan Šnajder
Transformer Megatron Decepticons Active Learning Text Classification Model Learning Transformer Based Pre Trained Language Model Transfer

April 14, 2023

Model Predictive Control with Self-supervised Representation Learning
Jonas Matthies, Muhammad Burhan Hafez, Mostafa Kotb, Stefan Wermter
Predictive Control Self Supervised Representation Learning Latent State Model Learning DeepMind Control Suite Hybrid MPC

April 13, 2023

Enhancing Model Learning and Interpretation Using Multiple Molecular Graph Representations for Compound Property and Activity Prediction
Apakorn Kengkanna, Masahito Ohue
Molecular Graph Abstract Interpretation Model Learning Activity Prediction Compound Property

April 3, 2023

Data-Efficient Policy Selection for Navigation in Partial Maps via Subgoal-Based Abstraction
Abhishek Paudel, Gregory J. Stein
Local Navigation Model Learning Offline Policy Evaluation Thresholding Linear Bandit Policy Selection

March 9, 2023

PDSketch: Integrated Planning Domain Programming and Learning
Jiayuan Mao, Tomás Lozano-Pérez, Joshua B. Tenenbaum, Leslie Pack Kaelbling
LeArning Abstract Model Generalization Model Learning Heuristic Learning

February 8, 2023

Investigating the role of model-based learning in exploration and transfer
Jacob Walker, Eszter Vértes, Yazhe Li, Gabriel Dulac-Arnold, Ankesh Anand, Théophane Weber, Jessica B. Hamrick
Reinforcement Learning Transfer Learning Integral Role Environment Exploration Reward Signal Model Learning Model Based Agent Intrinsic Exploration

January 20, 2023

Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning
Zifan Wu, Chao Yu, Chen Chen, Jianye Hao, Hankz Hankui Zhuo
Model Based Reinforcement Learning Policy Learning Predictive Uncertainty High Level Plan Model Learning Stable Learning

December 12, 2022

MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
Nicklas Hansen, Yixin Lin, Hao Su, Xiaolong Wang, Vikash Kumar, Aravind Rajeswaran
Deep Reinforcement Learning Noisy Demonstration Model Learning Visuo Motor Control Visual Model Based

November 23, 2022

Safety Analysis of Autonomous Driving Systems Based on Model Learning
Renjue Li, Tianhang Qin, Pengfei Yang, Cheng-Chao Huang, Youcheng Sun, Lijun Zhang
Autonomous Driving Traffic Scenario Model Learning Safety Analysis

November 4, 2022

The Benefits of Model-Based Generalization in Reinforcement Learning
Kenny Young, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber
Reinforcement Learning Model Based Reinforcement Learning Complementary Benefit Model Generalization Experience Replay Model Learning Learned Model

October 27, 2022

Disentangled and Robust Representation Learning for Bragging Classification in Social Media
Xiang Li, Yucheng Zhou
Classification Code Social Medium Domain Adversarial Model Learning Robust Representation Learning

October 18, 2022

A Survey of Active Learning for Natural Language Processing
Zhisong Zhang, Emma Strubell, Eduard Hovy
Natural Language Processing Timely Survey Active Learning Model Learning Structured Prediction

October 15, 2022

When to Update Your Model: Constrained Model-based Reinforcement Learning
Tianying Ji, Yu Luo, Fuchun Sun, Mingxuan Jing, Fengxiang He, Wenbing Huang
Full Model Policy OpTimization Constrained Reinforcement Learning Model Learning

October 12, 2022

ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characters
Heyuan Yao, Zhenhua Song, Baoquan Chen, Libin Liu
Variational Autoencoders Model Learning Physic Based Character Generative Control

October 11, 2022

Digital Twin-Based Multiple Access Optimization and Monitoring via Model-Driven Bayesian Learning
Clement Ruah, Osvaldo Simeone, Bashir Al-Hashimi
Multi Agent Reinforcement Learning Digital Twin Expert Driven Monitoring Model Learning Bayesian Model Communication System

October 3, 2022

Probabilistic Safeguard for Reinforcement Learning Using Safety Index Guided Gaussian Process Models
Weiye Zhao, Tairan He, Changliu Liu
Reinforcement Learning Black Box Model Safety Guarantee Model Learning Safe Controller Forward Invariance

June 27, 2022

Pen and Paper Exercises in Machine Learning
Michael U. Gutmann
Machine Learning Hidden Markov Model Graphical Model Model Learning Undirected Graphical Model Pen Like Object

June 22, 2022

Adaptive Attitude Estimation Using a Hybrid Model-Learning Approach
Eran Vertzberger, Itzik Klein
Efficient Hybrid Hybrid Deep Learning Model Learning Accelerometer Signal Inertial Sensor Attitude Estimation