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

12 results for “subnets”

Common Risk Factors in Decentralized AI Subnetsq-fin.PM

Derives a size premium from automated market makers in decentralized AI subnets.

problem Determining the profitability and risk of decentralized AI subnets.

method Analyzes daily data on 128 subnets, tests the size premium, and calculates transaction costs.

result The size premium is reduced by a halving of token emissions but remains profitable only below a certain asset threshold.

decentralized AI automated market makers subnets size premium token emissions

2026-03-31abs ↗pdf ↗

Representation Learning-Assisted Click-Through Rate Predictioncs.LG

Click-through rate (CTR) prediction is a critical task in online advertising systems. Most existing methods mainly model the feature-CTR relationship and suffer from the data sparsity issue. In this paper, we propose DeepMCP, which models other types of relationships in order to learn more informative and statistically…

2019-06-11abs ↗pdf ↗

Distributed Learning of Deep Neural Networks using Independent Subnet Trainingcs.LG

IST trains neural networks locally, reducing memory and communication costs.

problem Challenges in distributed learning due to mandatory data separation.

method Independent subnet training (IST) decomposes the network into narrow subnetworks.

result IST reduces training times compared to common distributed learning approaches.

distributed learning deep neural networks model parallelism memory usage communication costs

2019-10-04abs ↗pdf ↗

On a discretization of confocal quadrics. I. An integrable systems approachmath.DG

Confocal quadrics lie at the heart of the system of confocal coordinates (also called elliptic coordinates, after Jacobi). We suggest a discretization which respects two crucial properties of confocal coordinates: separability and all two-dimensional coordinate subnets being isothermic surfaces (that is, allowing a con…

2015-11-05abs ↗pdf ↗

An example for a nontrivial irreducible geodesic net in the planemath.MG

We construct a geodesic net in the plane with four unbalanced (boundary) vertices that has 16 balanced vertices and does not contain proper geodesic subnets. This is the first example of an irreducible geodesic net in the Euclidean plane with 4 boundary vertices that is not a tree.

2019-02-21abs ↗pdf ↗

Voice and accompaniment separation in music using self-attention convolutional neural networkeess.AS

A new neural network separates vocals from music accompaniment.

problem Separating vocals from music accompaniment in recordings.

method Self-attention convolutional neural network (CNN) with densely-connected blocks.

result 19.5% relative improvement in vocals separation.

music separation voice separation self-attention convolutional neural network music accompaniment

2020-03-19abs ↗pdf ↗

Option Pricing on Automated Market Maker Tokensq-fin.PR

Derives token price process for AMM tokens, finds leverage effect and pricing discrepancies.

problem Derives token price process for AMM tokens.

method Derives CEV process for token price, derives closed-form option prices, introduces liquidity-adjusted Greeks.

result Token price process is CEV, with leverage effect and pricing discrepancies.

automated market maker CEV process option pricing leverage effect implied volatility skew

2026-03-31abs ↗pdf ↗

A Multi-component CNN-RNN Approach for Dimensional Emotion Recognition in-the-wildcs.CV

This paper presents our approach to the One-Minute Gradual-Emotion Recognition (OMG-Emotion) Challenge, focusing on dimensional emotion recognition through visual analysis of the provided emotion videos. The approach is based on a Convolutional and Recurrent (CNN-RNN) deep neural architecture we have developed for the …

2018-05-03abs ↗pdf ↗

Industry-Scale Orchestrated Federated Learning for Drug Discoverycs.LG

Federated learning platform for drug discovery without sharing data.

problem Lack of secure collaboration in drug discovery.

method Industry-scale federated learning platform using cryptographic aggregation.

result Generated new scientific discoveries in drug discovery.

federated learning drug discovery cryptographic aggregation industry collaboration IMI project

2022-10-17abs ↗pdf ↗

Towards Constructing Geodesic Nets with Four Boundary Vertices and an Increasing Number of Balanced Verticesmath.MG

A geodesic net with 4 boundary vertices and 25 balanced vertices is constructed.

problem Constructing geodesic nets with specific vertex types and properties.

method Novel approach to increase the number of balanced vertices from 16 to 25.

result First net with four boundary vertices and 25 balanced vertices, including non-symmetric balanced vertices.

geodesic nets balanced vertices irreducible nets four boundary vertices

2025-11-11abs ↗pdf ↗

Fine-Grained Urban Flow Inferencecs.CV

Paper presents UrbanFM and UrbanPy models for inferring fine-grained urban flows.

problem Reduce cost of urban flow monitoring while maintaining data accuracy and granularity.

method Develops UrbanFM and UrbanPy models to infer fine-grained urban flows from coarse-grained observations.

result UrbanPy model demonstrates favorable performance for larger-scale inference tasks.

Urban flow monitoring Fine-grained inference Crowd flow UrbanFM UrbanPy

2020-02-05abs ↗pdf ↗

Exploiting multi-CNN features in CNN-RNN based Dimensional Emotion Recognition on the OMG in-the-wild Datasetcs.LG

Paper presents a CNN-RNN method for multi-dimensional emotion recognition in-the-wild.

problem Dimensional emotion recognition in real-world scenarios.

method Pre-training with Aff-Wild and Aff-Wild2, extracting low-, mid-, and high-level features, using RNN subnets in a multi-task framework, and fusion of networks.

result Our approach outperformed state-of-the-art methods using only visual information.

emotion recognition CNN-RNN multi-modal in-the-wild OMG-Emotion

2019-10-03abs ↗pdf ↗