Learned Model

Learned models encompass a broad range of machine learning approaches aiming to create accurate and efficient predictive systems. Current research emphasizes improving model robustness, generalization, and efficiency through techniques like self-distillation, hierarchical contrastive learning, and test-time adaptation, often employing neural networks, ordinary differential equations, and automaton models. These advancements are crucial for addressing challenges in various fields, including reinforcement learning, domain generalization, and fairness in machine learning, ultimately leading to more reliable and trustworthy AI systems. Furthermore, research focuses on mitigating issues like catastrophic forgetting and spurious correlations to enhance model performance and applicability.

Papers

November 7, 2024

Interpreting the Learned Model in MuZero Planning
Hung Guei, Yan-Ru Ju, Wei-Yu Chen, Ti-Rong Wu
Dynamic Network Latent State Machine Translated Learned Model AlphaZero Algorithm

July 16, 2024

Approximating Probabilistic Inference in Statistical EL with Knowledge Graph Embeddings
Yuqicheng Zhu, Nico Potyka, Bo Xiong, Trung-Kien Tran, Mojtaba Nayyeri, Evgeny Kharlamov, Steffen Staab
Knowledge Graph Embeddings Description Logic Statistical Query Learned Model

July 5, 2024

Understanding the Gains from Repeated Self-Distillation
Divyansh Pareek, Simon S. Du, Sewoong Oh
Knowledge Distillation Self Distillation Regression Task Big Gain Learned Model

May 19, 2024

Switched Flow Matching: Eliminating Singularities via Switching ODEs
Qunxi Zhu, Wei Lin
Generative Model Neural Ordinary Differential Equation Flow Matching Ordinary Differential Equation Learned Model Singularity Free

April 1, 2024

Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models
Yi-Lin Tuan, Xilun Chen, Eric Michael Smith, Louis Martin, Soumya Batra, Asli Celikyilmaz, William Yang Wang, Daniel M. Bikel
Large Language Model Human SAFETY Use Case Learned Model Human Annotator Helpfulness Score

January 10, 2024

Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics
Nicolò Romandini, Alessio Mora, Carlo Mazzocca, Rebecca Montanari, Paolo Bellavista
Timely Survey NCD Method Evaluation Metric Learned Model Federated Unlearning Malicious Client General Data Protection Regulation Design Consideration

November 27, 2023

Stability-Informed Initialization of Neural Ordinary Differential Equations
Theodor Westny, Arman Mohammadi, Daniel Jung, Erik Frisk
Neural ODE Neural Ordinary Differential Equation Learned Model Robust Initialization Initialization Scheme

November 11, 2023

Stacked networks improve physics-informed training: applications to neural networks and deep operator networks
Amanda A Howard, Sarah H Murphy, Shady E Ahmed, Panos Stinis
Neural Network Financial Application Physic Informed Neural Network Deep Operator Network Learned Model Simulated Annealing Wave Equation Physic Informed Training

October 30, 2023

GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models
Mianchu Wang, Rui Yang, Xi Chen, Hao Sun, Meng Fang, Giovanni Montana
Policy OpTimization Learned Model Offline Planning Offline Goal Conditioned Reinforcement Learning Multi Goal Offline Goal Conditioned RL

October 24, 2023

Finetuning Offline World Models in the Real World
Yunhai Feng, Nicklas Hansen, Ziyan Xiong, Chandramouli Rajagopalan, Xiaolong Wang
Reinforcement Learning Real World Real Robot Learned Model State Action Distribution

October 19, 2023

CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning
Liyiming Ke, Yunchu Zhang, Abhay Deshpande, Siddhartha Srinivasa, Abhishek Gupta
Imitation Learning Robotics Domain Feature Imitation Learned Model Augmentation Consistency Demonstration Example Specific Invariance

June 19, 2023

Causal Effect Regularization: Automated Detection and Removal of Spurious Attributes
Abhinav Kumar, Amit Deshpande, Amit Sharma
Simple Classifier Automatic Detection Active Removal Spurious Feature Learned Model Causal Interventional Regularizer

June 8, 2023

Generalization Performance of Transfer Learning: Overparameterized and Underparameterized Regimes
Peizhong Ju, Sen Lin, Mark S. Squillante, Yingbin Liang, Ness B. Shroff
Transfer Learning Generalization Performance Overparametrization Bound Learned Model Parameterized Regime

April 10, 2023

Improved Test-Time Adaptation for Domain Generalization
Liang Chen, Yong Zhang, Yibing Song, Ying Shan, Lingqiao Liu
Domain Generalization Test Time Adaptation Consistency Loss Test Time Training Learned Model

March 30, 2023

Non-Invasive Fairness in Learning through the Lens of Data Drift
Ke Yang, Alexandra Meliou
Machine Learning LeArning Abstract Machine Learning Model Camera Lens Recent Trend Learned Model Data Drift Fairness Estimation

March 15, 2023

On the Benefits of Leveraging Structural Information in Planning Over the Learned Model
Jiajun Shen, Kananart Kuwaranancharoen, Raid Ayoub, Pietro Mercati, Shreyas Sundaram
Task Planning Sample Complexity Model Based Reinforcement Learning Complementary Benefit Q Function State Action Pair Structural Information Learned Model Grid World

March 13, 2023

Analysing the Masked predictive coding training criterion for pre-training a Speech Representation Model
Hemant Yadav, Sunayana Sitaram, Rajiv Ratn Shah
Pre Training Speech Representation Speaker Information Learned Model

March 1, 2023

The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms
Anirudh Vemula, Yuda Song, Aarti Singh, J. Andrew Bagnell, Sanjiban Choudhury
Practical Algorithm Model Based Reinforcement Learning Learned Model Regret Algorithm Lazy Search

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 12, 2022

Efficient Offline Policy Optimization with a Learned Model
Zichen Liu, Siyi Li, Wee Sun Lee, Shuicheng Yan, Zhongwen Xu
Monte Carlo Tree Search Offline Policy Learned Model Offline Policy Learning Atari Benchmark