On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “energy-agnostic”

Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobianscs.LG

This work relaxes energy constraints in self-attention layers for a more general analysis.

problem Understanding inherent biases and dynamics in self-attention layers without energy functions.

method Dynamical systems analysis and Jacobian matrix examination.

result Normalized dynamics are close to a critical state, indicating high inference performance.

self-attention dynamics energy-agnostic Lyapunov exponents regularization

2025-05-26abs ↗pdf ↗

Sustainable Edge Intelligence Through Energy-Aware Early Exitingeess.SY

Energy-efficient DL inference for IoT devices reduces power consumption and improves performance.

problem Energy inefficiency in deep learning models for IoT devices.

method Energy-aware early exiting policy to balance energy consumption and inference accuracy.

result Accuracy and service rate improved up to 25% and 35% respectively.

deep learning IoT energy harvesting early exiting sustainability

2023-05-23abs ↗pdf ↗

Energy-Harvesting Distributed Machine Learningcs.LG

Paper explores sustainable machine learning with energy harvesting.

problem Energy-efficient distributed machine learning in resource-constrained devices.

method Developed a practical learning framework with theoretical guarantees for distributed learning over energy-harvesting devices.

result Demonstrated significant performance improvement over non-harvesting benchmarks.

energy harvesting distributed machine learning convergence guarantees wireless networks edge computing

2021-02-10abs ↗pdf ↗

A Theoretical Framework for Energy-Aware Gradient Pruning in Federated Learningcs.LG

A new energy-efficient pruning method for federated learning.

problem Energy inefficiency in gradient sparsification for federated learning.

method Formalized energy-constrained projection problem and proposed Cost-Weighted Magnitude Pruning (CWMP).

result CWMP optimally balances performance and energy efficiency in federated learning.

Federated Learning Gradient Pruning Energy Efficiency Cost-Weighted Magnitude Pruning Pareto Frontier

2026-03-23abs ↗pdf ↗