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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “co-distillation”

Prior knowledge distillation based on financial time seriescs.LG

This paper distills financial indicators into neural networks to reduce noise and improve accuracy.

problem Reduction of non-stationary noise in financial time series data.

method Co-distillation of smaller networks trained on indicators to transfer prior knowledge and reduce overfitting.

result The proposed method outperforms traditional methods in terms of speed and accuracy on real financial datasets.

financial time series non-stationary noise neural networks prior knowledge co-distillation

2020-06-16abs ↗pdf ↗

CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimizationcs.LG

CoDistill-GRPO improves small models in GRPO by distilling knowledge from a larger model.

problem Small models in GRPO struggle with sparse rewards on difficult tasks.

method Simultaneously trains a large and small model using co-distillation and GRPO objectives.

result Significant improvement in small model performance over standard GRPO on mathematical benchmarks.

CoDistill-GRPO Group Relative Policy Optimization Knowledge Distillation Small Models Efficiency

2026-05-09abs ↗pdf ↗

Adaptive Distillation for Decentralized Learning from Heterogeneous Clientscs.LG

New method for decentralized learning from diverse clients.

problem Achieving high-performance global model from diverse client models.

method Decentralized Learning via Adaptive Distillation (DLAD).

result Demonstrates effectiveness of DLAD on multiple public datasets.

Decentralized Learning Federated Learning Distillation Heterogeneous Clients Confidence Aggregation

2020-08-18abs ↗pdf ↗