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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “Mnemonics”

Mnemonics Training: Multi-Class Incremental Learning without Forgettingcs.CV

Paper proposes mnemonics framework for MCIL without forgetting.

problem Learning new concepts without forgetting previous ones in MCIL.

method Automatic framework using bilevel optimizations for parameterizing and optimizing exemplars.

result Mnemonics exemplars surpass state-of-the-art performance.

MCIL Incremental Learning Catastrophic Forgetting Bilevel Optimization Mnemonics

2020-02-24abs ↗pdf ↗

Finding MNEMON: Reviving Memories of Node Embeddingscs.LG

Paper proposes a novel graph recovery attack from node embeddings.

problem Privacy risks of integrating graph embeddings with machine learning pipelines.

method Model-agnostic graph recovery attack exploiting preserved structural information in node embeddings.

result Adversaries can recover graph edges with decent accuracy from node embeddings alone.

graph embeddings privacy risks node recovery graph recovery attack

2022-04-14abs ↗pdf ↗

A mnemonic for the Lipshitz-Ozsváth-Thurston correspondencemath.GT

A new method converts knot Floer homology to immersed curves.

problem Calculating bordered invariants of knot complements.

method Handle attachment to convert twice-punctured disk to once-punctured torus.

result Recovers Lipshitz-Ozsváth-Thurston's bordered invariant result.

knot Floer homology immersed curves handle attachment bordered invariants knot complements

2020-05-06abs ↗pdf ↗

Risk Management via Anomaly Circumvent: Mnemonic Deep Learning for Midterm Stock Predictionq-fin.ST

Midterm stock price prediction is crucial for value investments in the stock market. However, most deep learning models are essentially short-term and applying them to midterm predictions encounters large cumulative errors because they cannot avoid anomalies. In this paper, we propose a novel deep neural network Mid-LS…

2019-08-03abs ↗pdf ↗

BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularizationcs.NE

BEAN models neuronal correlations to create interpretable representations.

problem Hard interpretation of dense-layer representations in DNNs.

method Inspired by neuroscience, BEAN models neuronal correlations and dependencies.

result BEAN enables formation of interpretable neuronal clusters without sacrificing model performance.

neural networks representation learning cell assemblies biological neurons sparse models

2019-09-27abs ↗pdf ↗