Efficient Learning

Efficient learning focuses on developing algorithms and models that achieve high performance with minimal computational resources and training data. Current research emphasizes improving the efficiency of various machine learning paradigms, including reinforcement learning (through techniques like object-centric abstraction and low interaction rank), graphical models (with optimized solvers and sparse representations), and deep learning (via methods such as Low-Rank Adaptation and random Fourier neural networks). These advancements are crucial for deploying machine learning in resource-constrained environments and for accelerating the training of increasingly complex models, impacting fields ranging from robotics and healthcare to scientific discovery.

Papers

November 29, 2023

Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning
Lisheng Wu, Ke Chen
Efficient Learning Goal Conditioned Reinforcement Learning Policy Improvement

November 10, 2023

Efficient Learning of Fast Inverse Kinematics with Collision Avoidance
Johannes Tenhumberg, Arman Mielke, Berthold Bäuml
Collision Avoidance Efficient Learning Inverse Kinematics Robot Motion Planning Complex Robotic System

November 9, 2023

October 25, 2023

Toward the use of proxies for efficient learning manipulation and locomotion strategies on soft robots
Etienne Ménager, Quentin Peyron, Christian Duriez
Motion Planning Greater Public Use Soft Robot Humanoid Robot Efficient Learning Human Like Locomotion Behavior Proxy Dataset Rigid Robot Locomotion Strategy

October 13, 2023

September 13, 2023

Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains
Md Nasim, Yexiang Xue
Partial Differential Equation Efficient Learning Compressed Model PDE Model Taylor Expansion Sparse Decomposition Fourier Domain

August 24, 2023

Masked Autoencoders are Efficient Class Incremental Learners
Jiang-Tian Zhai, Xialei Liu, Andrew D. Bagdanov, Ke Li, Ming-Ming Cheng
Class Incremental Learning Masked Autoencoders Efficient Learning Incremental Learning Framework

August 18, 2023

Integrating Expert Guidance for Efficient Learning of Safe Overtaking in Autonomous Driving Using Deep Reinforcement Learning
Jinxiong Lu, Gokhan Alcan, Ville Kyrki
Deep Reinforcement Learning Autonomous Driving Autonomous Vehicle Autonomous System Efficient Learning Safe Overtaking

August 14, 2023

Efficient Learning of Quantum States Prepared With Few Non-Clifford Gates II: Single-Copy Measurements
Sabee Grewal, Vishnu Iyer, William Kretschmer, Daniel Liang
Efficient Learning Efficient Algorithm Quantum State N$ Qubit Measurement Operator Time Algorithm Unitary Gate

August 7, 2023

Provably Efficient Learning in Partially Observable Contextual Bandit
Xueping Gong, Jiheng Zhang
Efficient Learning Bandit Algorithm Causal Constraint

July 26, 2023

Efficient Learning of Discrete-Continuous Computation Graphs
David Friede, Mathias Niepert
Efficient Learning Stochastic Network Computation Graph

June 12, 2023

Differentiable Multi-Fidelity Fusion: Efficient Learning of Physics Simulations with Neural Architecture Search and Transfer Learning
Yuwen Deng, Wang Kang, Wei W. Xing
Deep Learning Transfer Learning Neural Architecture Search Surrogate Model Efficient Learning Multi Fidelity Physical Simulation Closed Form Differentiable Expression Training Sample

June 11, 2023

Efficient Learning of Minimax Risk Classifiers in High Dimensions
Kartheek Bondugula, Santiago Mazuelas, Aritz Pérez
Support Vector Machine High Dimension Efficient Learning Minimax Risk Classifier

June 10, 2023

TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials
Guillem Simeon, Gianni de Fabritiis
Efficient Learning 3D Equivariance Molecular Energy Cartesian Tensor

June 1, 2023

Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks
Dan Zhao
Deep Network Efficient Learning Implicit Bias Implicit Regularization Deep Linear Explicit Regularization Explicit Point Solo

May 31, 2023

Efficient Learning of Urban Driving Policies Using Bird's-Eye-View State Representations
Raphael Trumpp, Martin Büchner, Abhinav Valada, Marco Caccamo
Reinforcement Learning Autonomous Driving Bird'S Eye View Efficient Learning Deep Reinforcement Urban Driving Recurrent Neural Network Architecture

May 28, 2023

Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
Zixuan Hu, Li Shen, Zhenyi Wang, Baoyuan Wu, Chun Yuan, Dacheng Tao
LeArning Abstract Black Box Efficient Learning API Usage Meta Distillation

May 26, 2023

Exploiting Large Neuroimaging Datasets to Create Connectome-Constrained Approaches for more Robust, Efficient, and Adaptable Artificial Intelligence
Erik C. Johnson, Brian S. Robinson, Gautam K. Vallabha, Justin Joyce, Jordan K. Matelsky, Raphael Norman-Tenazas, Isaac Western, Marisel Villafañe-Delgado, Martha Cervantes, Michael S. Robinette, Arun V. Reddy, Lindsey Kitchell, Patricia K. Rivlin, Elizabeth P. Reilly, Nathan Drenkow, Matthew J. Roos, I-Jeng Wang, Brock A. Wester, William R. Gray-Roncal, Joan A. Hoffmann
Data Set High Efficiency Single Neuron Level Efficient Learning Deep Learning Network Neural System Adaptive AI

Efficient Learning

Papers

Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning

Efficient Learning of Fast Inverse Kinematics with Collision Avoidance

DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency

Accelerated Shapley Value Approximation for Data Evaluation

Toward the use of proxies for efficient learning manipulation and locomotion strategies on soft robots

Fast & Efficient Learning of Bayesian Networks from Data: Knowledge Discovery and Causality

Progressively Efficient Learning

Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains

Masked Autoencoders are Efficient Class Incremental Learners

Integrating Expert Guidance for Efficient Learning of Safe Overtaking in Autonomous Driving Using Deep Reinforcement Learning

Efficient Learning of Quantum States Prepared With Few Non-Clifford Gates II: Single-Copy Measurements

Provably Efficient Learning in Partially Observable Contextual Bandit

Efficient Learning of Discrete-Continuous Computation Graphs

Differentiable Multi-Fidelity Fusion: Efficient Learning of Physics Simulations with Neural Architecture Search and Transfer Learning

Efficient Learning of Minimax Risk Classifiers in High Dimensions

TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials

Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks

Efficient Learning of Urban Driving Policies Using Bird's-Eye-View State Representations

Learning to Learn from APIs: Black-Box Data-Free Meta-Learning

Exploiting Large Neuroimaging Datasets to Create Connectome-Constrained Approaches for more Robust, Efficient, and Adaptable Artificial Intelligence