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

3 results for “meta-learnt”

MetaNOR: A Meta-Learnt Nonlocal Operator Regression Approach for Metamaterial Modelingcond-mat.mtrl-sci

MetaNOR learns common nonlocal kernels for efficient metamaterial modeling.

problem Efficiently modeling wave propagation in new metamaterials.

method Meta-learns a common nonlocal kernel from existing tasks and transfers this knowledge to new tasks with minimal data.

result Substantial improvements in sampling efficiency for new metamaterials.

meta-learnt nonlocal operator transfer-learning metamaterials wave propagation

2022-06-04abs ↗pdf ↗

Meta-learnt priors slow down catastrophic forgetting in neural networkscs.AI

Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model is not given any knowledge of anything outside its (single-task) training distribution, and has thus no way to learn parameters (i.e., featu…

2019-09-09abs ↗pdf ↗

Meta-Learning of Exploration/Exploitation Strategies: The Multi-Armed Bandit Casecs.AI

The exploration/exploitation (E/E) dilemma arises naturally in many subfields of Science. Multi-armed bandit problems formalize this dilemma in its canonical form. Most current research in this field focuses on generic solutions that can be applied to a wide range of problems. However, in practice, it is often the case…

2012-07-22abs ↗pdf ↗