Many Parameter

Research on "many parameter" models focuses on optimizing the number and utilization of parameters in various machine learning architectures to improve efficiency and performance. Current efforts concentrate on developing parameter-efficient fine-tuning techniques, exploring different model architectures like transformers and graph convolutional networks, and investigating the impact of parameter count on model capabilities and generalization. This research is significant because it addresses the computational cost and resource limitations associated with large models, enabling wider accessibility and applicability across diverse fields, including medical imaging, robotics, and natural language processing.

Papers

March 14, 2022

Simultaneous Learning of the Inputs and Parameters in Neural Collaborative Filtering
Ramin Raziperchikolaei, Young-joo Chung
Recommender System Many Parameter Rich Input Shallow Network Learnable Parameter Item Embeddings Simultaneous Learning Neural Collaborative Filtering

March 2, 2022

ParaPose: Parameter and Domain Randomization Optimization for Pose Estimation using Synthetic Data
Frederik Hagelskjaer, Anders Glent Buch
Deep Learning Synthetic Data Pose Estimation Human Pose Many Parameter Synthetic Training Data Domain Randomization

February 6, 2022

No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models
Chen Liang, Haoming Jiang, Simiao Zuo, Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen, Tuo Zhao
Neural Machine Translation Generalization Performance Learning Rate Many Parameter Information Redundancy Feature Redundancy Large Transformer Model

February 3, 2022

Modeling unknown dynamical systems with hidden parameters
Xiaohan Fu, Weize Mao, Lo-Bin Chang, Dongbin Xiu
Deep Neural Network Dynamical System Many Parameter

February 2, 2022

December 31, 2021

Inferring perceptual decision making parameters from behavior in production and reproduction tasks
Nils Neupärtl, Constantin A. Rothkopf
Bayesian Inference Many Parameter BEHAVIOR Explanation Serial Reproduction Production Incident Perceptual Uncertainty Psychophysical Task

December 29, 2021

The impacts of various parameters on learning process and machine learning based performance prediction in online coding competitions
Hardik Patel, Purvi Koringa
Machine Learning Model New Machine Many Parameter Complex Process Competition Platform Performance Prediction Machine Learning Classifier Competition Result Online Questionnaire

December 16, 2021

BoGraph: Structured Bayesian Optimization From Logs for Expensive Systems with Many Parameters
Sami Alabed, Eiko Yoneki
Bayesian Optimization Probabilistic Model Many Parameter Structure Learning Parameter Space Log Message Auto Tuning

November 10, 2021

Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters
Xiangru Lian, Binhang Yuan, Xuefeng Zhu, Yulong Wang, Yongjun He, Honghuan Wu, Lei Sun, Haodong Lyu, Chengjun Liu, Xing Dong, Yiqiao Liao, Mingnan Luo, Congfei Zhang, Jingru Xie, Haonan Li, Lei Chen, Renjie Huang, Jianying Lin, Chengchun Shu, Xuezhong Qiu, Zhishan Liu, Dongying Kong, Lei Yuan, Hai Yu, Sen Yang, Ce Zhang, Ji Liu
Deep Learning Many Parameter Recommendation Model Parallel Training Hybrid System Dense Neural Network Persian Text

November 4, 2021

Optimal Recovery from Inaccurate Data in Hilbert Spaces: Regularize, but what of the Parameter?
Simon Foucart, Chunyang Liao
Regularization Model Many Parameter Regularization Parameter Hilbert Space Functional Theory Orthonormal Basis Optimal Recovery

Many Parameter

Papers

Simultaneous Learning of the Inputs and Parameters in Neural Collaborative Filtering

ParaPose: Parameter and Domain Randomization Optimization for Pose Estimation using Synthetic Data

No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models

Modeling unknown dynamical systems with hidden parameters

Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference

Unified Scaling Laws for Routed Language Models

Inferring perceptual decision making parameters from behavior in production and reproduction tasks

The impacts of various parameters on learning process and machine learning based performance prediction in online coding competitions

BoGraph: Structured Bayesian Optimization From Logs for Expensive Systems with Many Parameters

Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters

Optimal Recovery from Inaccurate Data in Hilbert Spaces: Regularize, but what of the Parameter?