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

7 results for “bit-budget”

Moniqua: Modulo Quantized Communication in Decentralized SGDcs.LG

Moniqua improves SGD convergence with quantized communication.

problem Efficiently communicating in decentralized SGD with limited bandwidth.

method Modulo quantized communication in decentralized SGD.

result Moniqua converges at the same rate as full-precision communication with less bits.

decentralized SGD quantized communication asymptotic rate bit-budget 1-bit quantization

2020-02-26abs ↗pdf ↗

Minimax Optimal Quantization of Linear Models: Information-Theoretic Limits and Efficient Algorithmscs.IT

This work optimizes quantization of linear models to reduce memory usage.

problem Optimizing memory usage for high-dimensional linear models.

method Information-theoretic framework with randomized embedding-based algorithms.

result Matching upper and lower bounds for minimax risk under quantization constraints.

quantization linear models information theory minimax risk embedding algorithms

2022-02-23abs ↗pdf ↗

Quantum Tunneling-Aware Machine Learning: Physics-Derived Noise Models for Robust Deploymentcs.LG

QTAML models quantum tunneling errors for AI robustness.

problem Quantum tunneling errors in AI inference.

method Derives weight-error distribution using WKB approximation, introduces TAC algorithm.

result TAC achieves 95% clean accuracy with 3.4-33.6x less ECC overhead.

quantum tunneling machine learning AI robustness WKB approximation Tunneling-Aware Compensation

2026-05-30abs ↗pdf ↗

Few Batches or Little Memory, But Not Both: Simultaneous Space and Adaptivity Constraints in Stochastic Banditscs.LG

New constraints on space and adaptivity in bandits force more batches and memory use.

problem Simultaneous space and adaptivity constraints in stochastic bandits.

method Proved lower bounds and constructed an algorithm with near-minimax regret.

result Near-minimax regret requires more batches and memory than previously thought.

stochastic bandits space constraints adaptivity constraints near-minimax regret information bottleneck

2026-03-14abs ↗pdf ↗

Compressing Large Language Models using Low Rank and Low Precision Decompositioncs.LG

CALDERA compresses large language models by approximating weight matrices with low-rank, low-precision factors.

problem The large sizes of Large Language Models (LLMs) hinder deployment on edge devices.

method CALDERA approximates weight matrices

\mathbf{W}

\mathbf{Q} + \mathbf{L}\mathbf{R}

, where

\mathbf{L}

and

\mathbf{R}

are low-rank factors quantized to low precision.

result CALDERA achieves better zero-shot performance than existing techniques, especially with low bit precision.

Large Language Models Compression Low-Rank Approximation Low-Precision Edge Devices

2024-05-29abs ↗pdf ↗

Matrix Compression via Randomized Low Rank and Low Precision Factorizationcs.LG

Algorithm compresses large matrices by approximating them as low rank and low precision factors.

problem Efficiently storing and processing large matrices with billions of elements.

method Randomized sketching and quantization of matrix columns to achieve low rank and low precision factorization.

result Achieves compression ratios as low as one bit per matrix coordinate while maintaining or improving performance.

matrix compression low rank factorization randomized algorithms quantization image processing

2023-10-17abs ↗pdf ↗

Batched Stochastic Linear Bandits with 1-Bit Communication Constraintsstat.ML

New algorithm tackles batched stochastic linear bandits with 1-bit communication constraints.

problem Stochastic linear bandits with 1-bit communication constraints.

method Phased-elimination algorithms based on G-optimal designs and 1-bit mean estimation.

result Achieves near-optimal regret bounds for broad scaling regimes.

stochastic linear bandits batched 1-bit communication minimax regret G-optimal designs

2026-05-29abs ↗pdf ↗