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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “grow-and-prune”

Grow and Prune Compact, Fast, and Accurate LSTMscs.LG

Grow and prune LSTM to reduce parameters and latency.

problem Model redundancy, increased run-time delay, and overfitting in deep LSTM models.

method Hidden-layer LSTM (H-LSTM) with grow-and-prune (GP) training.

result Significant reduction in parameters, latency, and improvement in accuracy.

LSTM hidden layers grow-and-prune image captioning speech recognition

2018-05-30abs ↗pdf ↗

Growing Efficient Deep Networks by Structured Continuous Sparsificationcs.LG

New method grows deep networks efficiently by dynamically pruning and growing layers.

problem Training deep networks is computationally expensive and inefficient.

method Structured continuous sparsification starting from a small seed architecture.

result 49.7% inference FLOPs and 47.4% training FLOPs savings with 75.2% top-1 accuracy.

deep learning network pruning continuous relaxation dynamic growth FLOPs reduction

2020-07-30abs ↗pdf ↗

On Mixing Rates for Bayesian CARTmath.ST

This work improves mixing rates for Bayesian CART, a key component of BART.

problem Understanding and improving mixing rates for Bayesian inference with MCMC.

method Derived upper bounds on mixing times, provided sufficient conditions for polynomial mixing, and proposed Twiggy Bayesian CART.

result Twiggy Bayesian CART achieves polynomial mixing without assuming signal connectivity.

Bayesian CART MCMC Mixing Rates Wavelets Twiggy

2023-05-31abs ↗pdf ↗

Autonomous Deep Learning: Continual Learning Approach for Dynamic Environmentscs.LG

ADL uses a self-constructing network to handle dynamic data streams.

problem Catastrophic forgetting in deep neural networks.

method ADL employs a flexible network structure with drift detection and pruning mechanisms.

result ADL consistently outperforms other continual learning methods in dynamic environments.

continual learning catastrophic forgetting dynamic environments self-constructing network drift detection

2018-10-17abs ↗pdf ↗