Research
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

19395877 · May 202619922001200920182026
48 results for syllable decomposition

Syllable-aware models perform similarly to character-based ones but use fewer parameters and train faster.

problem Improving word-level language modeling performance with syllable-based models.
method Used a syllable-aware neural language model with fewer parameters and faster training.
result Achieved comparable performance to character-based models but with 18%-33% fewer parameters and 1.2-2.2 times faster training.

End-to-end transformer model improves lexical stress detection accuracy.

problem Inaccurate phoneme boundaries and limited features for stress classification.
method End-to-end sequence to sequence model using transformer trained on feature sequences and phoneme sequences with stress marks.
result End-to-end model achieves better performance and lower phoneme error rate (6.36%) compared to syllable segmentation methods.

Study on finiteness property of right-angled Artin groups actions on extension graphs.

problem Finiteness property of hyperbolic simplicial actions on right-angled Artin groups.
method Analysis of right-angled Artin group actions on extension graphs, using asymptotic translation lengths and syllable lengths.
result Asymptotic translation lengths of elements in right-angled Artin groups are rational and have a common denominator under certain conditions.

New techniques reuse subword embeddings in neural models, reducing size and improving performance.

problem Improving performance and reducing model size in subword-aware neural language models.
method Reusing subword embeddings and other weights in multi-layer input embedding models, tying layers consecutively bottom-up.
result Best morpheme-aware model with reused weights outperforms competitive word-level model by a large margin.

The paper proposes and discusses semiorthogonal decompositions for moduli spaces of vector bundles.

problem Decompositions of moduli spaces of vector bundles with fixed determinant of odd degree.
method Semiorthogonal decompositions, Grothendieck ring of varieties, mirror symmetry, graph potentials, Fukaya category.
result Evidence for a conjectural semiorthogonal decomposition of moduli spaces of rank 2 bundles with odd determinant.

New complexity notion connects finite decomposition and asymptotic property C.

problem Understanding and connecting different properties in metric spaces.
method Introducing finite APC-decomposition complexity and proving its implications.
result Finite APC-decomposition complexity implies property A for metric spaces.

Paper studies polynomial decomposition in system identification and machine learning.

problem Identifying a polynomial decomposition model in system identification and machine learning.
method Introduces X-rank decomposition and proves results on generic/maximal rank and identifiability.
result Proves new results on identifiability of a polynomial decomposition model.

Characterizes conditions for quotient spaces of decompositions to be manifolds.

problem Conditions for quotient spaces of decompositions to be manifolds.
method Generalized characterizations of upper semi-continuity for decomposition into one for a class decomposition.
result Characterizations of necessary and sufficient conditions for quotient spaces of decompositions to be kk-manifolds (k=1,2k = 1, 2).

The paper establishes new tools for studying decomposition complexity in metric spaces.

problem Understanding decomposition complexity in metric spaces.
method Three equivalent definitions for decomposition complexity are provided, and new methods are discussed to show metric spaces do not have finite decomposition complexity.
result Metric spaces with finite hyperbolic dimension have finite (weak) decomposition complexity.

Study shows OAT decomposition generates unexplained profit and loss, while SU decompositions depend on risk factor order.

problem Understanding profit and loss attribution in financial markets.
method Used financial market data from 2003 to 2022 to compare OAT, SU, and ASU decompositions.
result SU decompositions are sensitive to risk factor order and cannot identify all relevant risk factors.

New tensor network decompositions improve CNN performance.

problem Limited exploration of tensor network decompositions for CNNs.
method Characterized a new class of CNN modules and experimentally compared various decompositions.
result Some nonlinear decompositions outperform existing ones in terms of accuracy and efficiency.

A double pants decomposition of a 2-dimensional surface is a collection of two pants decomposition of this surface introduced in arXiv:1005.0073v2. There are two natural operations acting on double pants decompositions: flips and handle twists. It is shown in arXiv:1005.0073v2 that the groupoid generated by flips and h…

2010-08-22abs ↗pdf ↗

Let J1\mathcal{J}^1 be the real form of a complex simple Jordan algebra such that the automorphism group is F4(20)\mathrm{F}_{4(-20)}. By using some orbit types of F4(20)\mathrm{F}_{4(-20)} on J1\mathcal{J}^1, for F4(20)\mathrm{F}_{4(-20)}, explicitly, we give the Iwasawa decomposition, the Oshima--Sekiguchi's KεK_ε-Iwasawa decomp…

2011-09-05abs ↗pdf ↗

We study the topological types of pants decompositions of a surface by associating to any pants decomposition P,P, in a natural way its pants decomposition graph, Γ(P).Γ(P). This perspective provides a convenient way to analyze the maximum distance in the pants complex of any pants decomposition to a pants decomposition c…

2011-06-07abs ↗pdf ↗

New method uses random decompositions for high-dimensional Bayesian optimization.

problem Learning accurate decompositions for high-dimensional black-box functions.
method Data-independent random tree-based decomposition sampling.
result Random decomposition upper-confidence bound algorithm (RDUCB) yields significant empirical gains.

Derive new Euler-Ramanujan-type identities and infinite decompositions for zero mean curvature graphs in various spaces.

problem Derive new Euler-Ramanujan-type identities and infinite decompositions for zero mean curvature graphs in various spaces.
method Derive new Euler-Ramanujan-type identities and infinite decompositions for zero mean curvature graphs in various spaces.
result Derive new Euler-Ramanujan-type identities and infinite decompositions for zero mean curvature graphs in various spaces.

We give an example of two JSJ decompositions of a group that are not related by conjugation, conjugation of edge-inclusions, and slide moves. This answers the question of Rips and Sela stated in "Cyclic splittings of finitely presented groups and the canonical JSJ decomposition," Ann. of Math. 146 (1997), 53-109. On th…

2001-10-17abs ↗pdf ↗

Abstract: A new decomposition for gg-supermartingales without continuity.

problem Developing a new decomposition for gg-supermartingales.
method Providing a general Doob-Meyer decomposition for gg-supermartingale systems.
result Generalization of existing decompositions for supermartingales and right-continuous gg-supermartingales.

We consider a union of two pants decompositions of the same orientable 2-dimensional surface of any genus g. Each pants decomposition corresponds to some handlebody bounded by this surface, so two pants decompositions correspond to a Heegaard splitting of a 3-manifold. We introduce a groupoid FT acting on double pants …

2010-05-01abs ↗pdf ↗

Lefschetz decompositions for Kähler manifold eigenforms identified.

problem Understanding the spectrum and eigenspaces of Laplacians on Kähler manifolds.
method Analyzing the eigenspaces of the Laplacian ΔkΔ_k on kk-forms on a compact Kähler manifold.
result The positive part of the spectrum of ΔkΔ_k lies in the spectrum of Δk+1Δ_{k+1}.

Analyzes canonical reductive decomposition of extrinsic homogeneous submanifolds.

problem Understanding the reductive decomposition of extrinsic homogeneous submanifolds.
method Examines Lie subgroups and reductive decompositions of homogeneous structures.
result Establishes a connection with the Ambrose-Singer theorem and homogeneous structures.

The paper defines and proves stabilization for 3-manifold decompositions with multibranched surface intersections.

problem Decomposing 3-manifolds with more than 3 handlebodies and multibranched surface intersections.
method Definition and proof of stabilization operations for these decompositions.
result Stable equivalence of handlebody decompositions with multibranched surface intersections.