Partial Sum

Partial sums, representing the aggregation of sequential data or components, are a central theme in diverse fields, with research focusing on improving their efficiency, accuracy, and interpretability. Current efforts involve developing novel algorithms and model architectures, such as contextual normalized maximum likelihood and sum-of-squares circuits, to optimize partial sum calculations in various contexts, including machine learning, signal processing, and scientific computing. These advancements are crucial for enhancing the performance and efficiency of numerous applications, from deep neural network acceleration to robust statistical inference and improved understanding of complex systems.

Papers

October 26, 2024

Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning
Yuting Tang, Xin-Qiang Cai, Jing-Cheng Pang, Qiyu Wu, Yao-Xiang Ding, Masashi Sugiyama
Reinforcement Learning Reward Function Partial Sum Non Markovian Reward Reward Delay Markovian Reward

October 4, 2024

Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood
Ziyi Liu, Idan Attias, Daniel M. Roy
Context Information Minimax Regret Non Parametric Partial Sum Logarithmic Loss Sequential Probability Assignment

August 21, 2024

August 9, 2024

Decomposition of one-layer neural networks via the infinite sum of reproducing kernel Banach spaces
Seungcheol Shin, Myungjoo Kang
Microbial Decomposition Feature Space Partial Sum Layer Neural Network Kernel Banach Space

July 17, 2024

StoX-Net: Stochastic Processing of Partial Sums for Efficient In-Memory Computing DNN Accelerators
Ethan G Rogers, Sohan Salahuddin Mugdho, Kshemal Kshemendra Gupte, Cheng Wang
DNN Accelerator Automated Conversion Memory Computing Partial Sum

July 4, 2024

Entity-Level Sentiment: More than the Sum of Its Parts
Egil Rønningstad, Roman Klinger, Lilja Øvrelid, Erik Velldal
Sentiment Analysis Part Identification Sentiment Feature Partial Sum Sentence Level Sentiment Entity Level Sentiment Sentiment Expression

June 19, 2024

When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models
Ting-Yun Chang, Jesse Thomason, Robin Jia
Large Language Model Full Model Context Learning Classification Task State of the Art LLM Part Identification Accurate Model Partial Sum

March 15, 2024

The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation
Lei Wang, Ee-Peng Lim
Large Language Model Context Learning Sequential Recommendation Whole Body Partial Sum Effective Demonstration

February 9, 2024

More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation
Nico Catalano, Alessandro Maranelli, Agnese Chiatti, Matteo Matteucci
Semantic Segmentation Segmentation Based Approach Segmentation Mask Visual Feature Part Identification Partial Sum Backbone Network

November 5, 2023

Log-Concavity of Multinomial Likelihood Functions Under Interval Censoring Constraints on Frequencies or Their Partial Sums
Bruce Levin, Erik Learned-Miller
Convex Set Log Likelihood Multinomial Logistic Probability Simplex Partial Sum Dominant Low Frequency Right Censored Log Concavity

October 25, 2023

Sum-of-Parts: Faithful Attributions for Groups of Features
Weiqiu You, Helen Qu, Marco Gatti, Bhuvnesh Jain, Eric Wong
Line by Line Explanation Feature Wise Feature Attribution Group Setting Source Attribution Faithful Explanation Partial Sum Part Based Interpretable Mathematical Expression

May 13, 2023

The Whole Is Greater than the Sum of Its Parts: Improving DNN-based Music Source Separation
Ryosuke Sawata, Naoya Takahashi, Stefan Uhlich, Shusuke Takahashi, Yuki Mitsufuji
Whole Body Music Source Separation Part Identification Partial Sum Domain Loss Instrument Recognition

March 22, 2023

Anti-symmetric Barron functions and their approximation with sums of determinants
Nilin Abrahamsen, Lin Lin
High Dimensional Average Approximation Social Determinant Partial Sum Ab Initio Quantum Chemistry Barron Space Barron Function Antisymmetric Function

February 22, 2023

Some Might Say All You Need Is Sum
Eran Rosenbluth, Jan Toenshoff, Martin Grohe
Graph Neural Network Expressivity Transfer Partial Sum Specific GNN

February 13, 2023

The Sum of Its Parts: Visual Part Segmentation for Inertial Parameter Identification of Manipulated Objects
Philippe Nadeau, Matthew Giamou, Jonathan Kelly
Collaborative Robot Part Segmentation Part Identification Object Manipulation Partial Sum Inertial Parameter Identification Collaborative Robotic Arm Inertial Parameter

February 9, 2023

Nonlinear Random Matrices and Applications to the Sum of Squares Hierarchy
Goutham Rajendran
Financial Application Part Whole Hierarchy Random Matrix Convex Relaxation Large Matrix Partial Sum

September 16, 2022

Value Summation: A Novel Scoring Function for MPC-based Model-based Reinforcement Learning
Mehran Raisi, Amirhossein Noohian, Luc Mccutcheon, Saber Fallah
Reward Function Model Based Reinforcement Learning Policy Learning Optimal Trajectory Partial Sum Scoring Function

June 7, 2022

Robust Sparse Mean Estimation via Sum of Squares
Ilias Diakonikolas, Daniel M. Kane, Sushrut Karmalkar, Ankit Pensia, Thanasis Pittas
High Dimensional Optimal Sampling Partial Sum List Decodable Exclusive Square Activation Identity Covariance

March 30, 2022

Closed-Form Minkowski Sum Approximations for Efficient Optimization-Based Collision Avoidance
James Guthrie, Marin Kobilarov, Enrique Mallada
High Efficiency Collision Avoidance Motion Planning Problem Nonlinear Programming Partial Sum Collision Avoidance Constraint Optimization Solver

Partial Sum

Papers

Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning

Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood

The Whole Is Bigger Than the Sum of Its Parts: Modeling Individual Annotators to Capture Emotional Variability

Sum of Squares Circuits

Decomposition of one-layer neural networks via the infinite sum of reproducing kernel Banach spaces

StoX-Net: Stochastic Processing of Partial Sums for Efficient In-Memory Computing DNN Accelerators

Entity-Level Sentiment: More than the Sum of Its Parts

When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models

The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation

More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation

Log-Concavity of Multinomial Likelihood Functions Under Interval Censoring Constraints on Frequencies or Their Partial Sums

Sum-of-Parts: Faithful Attributions for Groups of Features

The Whole Is Greater than the Sum of Its Parts: Improving DNN-based Music Source Separation

Anti-symmetric Barron functions and their approximation with sums of determinants

Some Might Say All You Need Is Sum

The Sum of Its Parts: Visual Part Segmentation for Inertial Parameter Identification of Manipulated Objects

Nonlinear Random Matrices and Applications to the Sum of Squares Hierarchy

Value Summation: A Novel Scoring Function for MPC-based Model-based Reinforcement Learning

Robust Sparse Mean Estimation via Sum of Squares

Closed-Form Minkowski Sum Approximations for Efficient Optimization-Based Collision Avoidance