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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “rate-constrained”

Implicit Rate-Constrained Optimization of Non-decomposable Objectivescs.LG

A new method for optimizing non-decomposable metrics with constraints.

problem Optimizing complex machine learning objectives with thresholded constraints.

method Formulate rate-constrained optimization using the Implicit Function theorem and solve with gradient-based methods.

result Demonstrated effectiveness over existing methods on benchmark datasets.

machine learning optimization non-decomposable thresholded rate-constrained

2021-07-23abs ↗pdf ↗

Private Rate-Constrained Optimization with Applications to Fair Learningcs.LG

New method for private learning with fairness constraints.

problem Rate-constrained optimization under differential privacy.

method RaCO-DP, a DP variant of SGDA solving Lagrangian formulation.

result Empirical results show RaCO-DP outperforms existing methods.

private learning fairness constraints differential privacy SGDA histogram estimation

2025-05-28abs ↗pdf ↗

Constrained Learning with Non-Convex Lossescs.LG

Paper tackles constrained learning with non-convex losses, overcoming challenges with new approach.

problem Challenges in learning with non-convex losses and statistical constraints.

method Learning in the empirical dual domain, bounding empirical duality gap.

result Established a constrained counterpart to classical learning theory.

learning non-convex constraints empirical dual duality gap

2021-03-08abs ↗pdf ↗

UVeQFed: Universal Vector Quantization for Federated Learningcs.LG

UVeQFed tackles FL model compression over limited channels.

problem Efficiently transmitting trained models over rate-constrained channels.

method Universal vector quantization for FL (UVeQFed).

result UVeQFed minimizes distortion and converges to optimal model.

Federated Learning Quantization Compression Decentralized Training Rate-Limited Channels

2020-06-05abs ↗pdf ↗