No article text was recorded for this version.
gradient dimensionality reduction
Version 1 of 141 papers44 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models
- Blog: TRAK: Attributing Model Behavior at Scale
- Blog: Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning
- Blog: SEPARATE: A Simple Low-rank Projection for Gradient Compression in Modern Large-scale Model Training Process
- Blog: ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
- Blog: Distributed Optimization for Overparameterized Problems: Achieving Optimal Dimension Independent Communication Complexity
- Blog: Estimating informativeness of samples with Smooth Unique Information
- Blog: Communication-Computation Efficient Gradient Coding
- Blog: Diversity Measurement and Subset Selection for Instruction Tuning Datasets
- Blog: Capturing the Temporal Dependence of Training Data Influence
- Blog: Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability
- Blog: Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
- Blog: Efficient Estimation of Kernel Surrogate Models for Task Attribution
- Blog: Token-wise Influential Training Data Retrieval for Large Language Models
- Blog: CORE: Common Random Reconstruction for Distributed Optimization with Provable Low Communication Complexity
- Blog: Understanding Impact of Human Feedback via Influence Functions
- Blog: Selecting Auxiliary Data via Neural Tangent Kernels for Low-Resource Domains
- Blog: gMINT: Gradiant-based Membership Inference Test applied to Image Models
- Blog: Clustered Influence Functions
- Blog: SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems
- Blog: VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
- Blog: Secure Distributed Training at Scale
- Blog: Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation
- Blog: ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning
- Blog: Scalable Influence and Fact Tracing for Large Language Model Pretraining
- Blog: Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between Samples
- Blog: Fast and Memory Efficient Differentially Private-SGD via JL Projections
- Blog: Ensembles of Low-Rank Expert Adapters
- Blog: Intriguing Properties of Data Attribution on Diffusion Models
- Blog: Motion Attribution for Video Generation
- Blog: Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation
- Blog: Optimization and Learning With Randomly Compressed Gradient Updates
- Blog: Personalized Federated Learning towards Communication Efficiency, Robustness and Fairness
- Blog: SGD with low-dimensional gradients with applications to private and distributed learning
- Blog: Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback
- Blog: Federated Learning over Wireless Fading Channels
- Blog: TRAK: Attributing Model Behavior at Scale
- Blog: TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data
- Blog: Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach
- Blog: In Good GRACES: Principled Teacher Selection for Knowledge Distillation
- Blog: Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models
History & citation
Current · Permanent link
- This direction split from Gradient Sketching for Scalable Data Attribution (93% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_gradient_dimensionality_reduction_160d99ab,
title = {gradient dimensionality reduction},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-dimensionality-reduction/rdr_160d99ab71254c40a6fedbef84019761},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_gradient_dimensionality_reduction_160d99ab_v1,
title = {gradient dimensionality reduction},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-dimensionality-reduction/rdr_160d99ab71254c40a6fedbef84019761/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}