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.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

14 results for “iSTS”

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 ↗

Beyond Observations: Reconstruction Error-Guided Irregularly Sampled Time Series Representation Learningcs.LG

iTimER learns from reconstruction errors to represent irregularly sampled time series.

problem Learning from irregularly sampled time series with missing data.

method iTimER models reconstruction errors as a proxy for unobserved values, using a mixup strategy and a Wasserstein metric.

result iTimER outperforms state-of-the-art methods in classification, interpolation, and forecasting tasks.

time series irregular sampling representation learning reconstruction error self-supervised

2025-11-10abs ↗pdf ↗

Learning Effective Soliton Dynamics from Scattering Dataphysics.comp-ph

New method learns soliton dynamics from scattering data without assuming known equations.

problem Deriving soliton dynamics from scattering data without prior knowledge.

method Combining IST with weak-form system identification for data-driven discovery.

result Effective soliton dynamics models derived from observed scattering data.

soliton dynamics inverse scattering transform system identification scattering data shallow-water equations

2026-07-01abs ↗pdf ↗

IISCNLP at SemEval-2016 Task 2: Interpretable STS with ILP based Multiple Chunk Alignercs.CL

iMATCH aligns non-contiguous chunks for iSTS with ILP and outperforms other systems.

problem Addressing iSTS with explanatory chunk alignment and score assignment.

method iMATCH uses ILP for chunk alignment and Random Forest for similarity type/score assignment.

result iMATCH outperforms other systems in alignment score and overall score for students dataset.

iSTS chunk alignment ILP Random Forest semantic similarity

2016-05-04abs ↗pdf ↗

An Introduction to A-polynomials and their Mahler Measuresmath.GT

These are the notes of the three lectures I delivered at the mini-workshop "Knot Theory and Number Theory around the A-Polynomial" at the Instituto Superior Tecnico (IST) in Lisbon in January 2014. The goal of the lectures was to familiarize, both the author and, the audience with the A-polynomials and the connection b…

2014-01-29abs ↗pdf ↗

A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Datacs.LG

This paper reviews deep learning methods for handling irregularly sampled medical time series data.

problem Handling irregularly sampled medical time series data for personalized treatment and precise diagnosis.

method Summarizes and compares deep learning methods categorized by technology and task.

result Achieved good results in data imputation and downstream tasks.

deep learning irregularly sampled data medical time series data imputation downstream tasks

2020-10-23abs ↗pdf ↗

Contributions to Khovanov Homologymath.GT

Khovanov homology ist a new link invariant, discovered by M. Khovanov, and used by J. Rasmussen to give a combinatorial proof of the Milnor conjecture. In this thesis, we give examples of mutant links with different Khovanov homology. We prove that Khovanov's chain complex retracts to a subcomplex, whose generators are…

2008-10-05abs ↗pdf ↗

A geometric characterization of arithmetic Fuchsian groupsmath.DG

The trace set of a Fuchsian group $Γ$ ist the set of length of closed geodesics in the surface $Γ\backslash \mathbb{H}$ . Luo and Sarnak showed that the trace set of a cofinite arithmetic Fuchsian group satisfies the bounded clustering property. Sarnak then conjectured that the B-C property actually characterizes arithm…

2006-09-17abs ↗pdf ↗

Monotonicity of the first eigenvalue of the Laplace and the p-Laplace operators under a forced mean curvature flowmath.DG

In this paper, we would like to give an answer to \textbf{Problem 1} below issued firstly in [J. Mao, Eigenvalue estimation and some results on finite topological type, Ph.D. thesis, IST-UTL, 2013]. In fact, by imposing some conditions on the mean curvature of the initial hypersurface and the coefficient function of th…

2013-10-21abs ↗pdf ↗

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statisticscs.LG

LDAdam optimizes large models with low memory by adapting to lower-dimensional subspaces.

problem Training large models efficiently and accurately.

method Adaptive optimization in lower-dimensional subspaces with a new projection-aware update rule and error feedback mechanism.

result LDAdam achieves accurate and efficient training of language models.

optimization memory efficiency adaptive learning subspace optimization language models

2024-10-21abs ↗pdf ↗

WoodFisher: Efficient Second-Order Approximation for Neural Network Compressioncs.LG

WoodFisher improves neural network compression efficiency and accuracy.

problem Efficiently estimating inverse Hessian for neural network optimization.

method WoodFisher: a method to compute a faithful and efficient estimate of the inverse Hessian.

result WoodFisher significantly outperforms state-of-the-art methods for pruning neural networks.

Neural Network Compression Optimization Inverse Hessian Hessian-vector Products Pruning

2020-04-29abs ↗pdf ↗

Vectors of Higher Rank on a Hadamard Manifold with Compact Quotientmath.DG

<ENGLISH> Consider a closed, smooth manifold M of nonpositive sectional curvature. Write p:UM-> M for the unit tangent bundle over M and let R_> denote the subset consisting of all vectors of higher rank. This subset is closed and invariant under the geodesic flow on UM. We will define the structured dimension sdim(R_>…

2003-11-03abs ↗pdf ↗

Testing Effect Homogeneity and Confounding in High-Dimensional Experimental and Observational Studiesecon.EM

Framework tests CATE homogeneity across trials and evaluates confounding.

problem Assessing treatment effect consistency across randomized and observational studies.

method Leverages multiple randomized trials to test CATE homogeneity and compares with observational data.

result Identifies potential confounding and effect heterogeneity in treatment effects.

CATE homogeneity confounding experimental studies observational studies treatment effects

2026-02-23abs ↗pdf ↗

Assessment Formats and Student Learning Performance: What is the Relation?physics.ed-ph

Study examines how different assessment formats affect student learning in a data communications course.

problem Understanding how various assessment formats impact student learning outcomes.

method Comparing student learning outcomes across multiple assessment formats in a core data communications course at George Mason University.

result Collective assessment formats enhance student knowledge demonstration.

assessment formats student learning data communications George Mason University learning outcomes

2017-11-15abs ↗pdf ↗