Accelerator boosts energy efficiency for MANNs on FPGAs.
problem Efficiently running MANNs on accelerators designed for other NNs.
method Data flow architecture, inference thresholding.
result Higher energy efficiency compared to NVIDIA GPU.
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “MANNs”
Memory-augmented neural networks (MANNs) refer to a class of neural network models equipped with external memory (such as neural Turing machines and memory networks). These neural networks outperform conventional recurrent neural networks (RNNs) in terms of learning long-term dependency, allowing them to solve intrigui…
We give a shorter proof of the following theorem of Kathryn Mann \cite{M}: the identity component of the group of the compactly supported diffeomorphisms of cannot admit a nontrivial -action on , provided , and . We also give a new proof of another theorem of Mann: any…
Study of CB generating sets for infinite-type surfaces.
problem Understanding CB generating sets for infinite-type surfaces.
method Constructing CB generating sets for specific infinite-type surfaces.
result Examples of surfaces with and without CB generating sets.
DAM with MRL improves relational reasoning in MANNs.
problem Limited performance of associative memory networks on complex relational reasoning tasks.
method Distributed Associative Memory architecture with Memory Refreshing Loss.
result Enhanced relation reasoning performance of MANNs on long temporal sequence data.
New algorithm optimizes adaptive return level for Markowitz portfolios.
problem Finding an optimal return level for Markowitz portfolios when investor's risk appetite is unknown.
method Krasnoselskii-Mann Proximity Algorithm based on proximity operator and momentum technique.
result Significant improvements over state-of-the-art methods in portfolio optimization.
Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular challenge for deep learning. In this regard, various researches on "meta-learning…
ARMIN improves memory efficiency and lightness in neural networks.
problem Complex memory addressing and inefficient memory information exploitation in previous MANNs.
method ARMIN uses hidden state for automatic memory addressing and a novel RNN cell for memory integration.
result ARMIN achieves lower computational overhead and similar performances compared to vanilla LSTM.
Extends algorithms to solve minimization problems faster.
problem Solving minimization problems with sparsity-inducing regularizers.
method Extends semismooth Newton algorithms to take advantage of sparsity.
result The resulting algorithms are a specific case of the Krasnosel'skiĭ--Mann scheme.
Augmenting a neural network with memory that can grow without growing the number of trained parameters is a recent powerful concept with many exciting applications. We propose a design of memory augmented neural networks (MANNs) called Labeled Memory Networks (LMNs) suited for tasks requiring online adaptation in class…
Classifies pure mapping class groups based on surface properties.
problem Classifying pure mapping class groups based on surface properties.
method Complete classification without additional assumptions.
result PMap(Σ) is globally CB if and only if Σ is the Loch Ness monster surface.
A three dimensional supergravity theory which generalizes the super IG theory of Witten and resembles the model discussed recently by Mann and Papadopoulos is displayed. The partition function is computed, and is shown to be a three-manifold invariant generalizing the Casson invariant.
The study examines when mapping class groups are quasi-isometric to graphs of curves.
problem When is the mapping class group of an infinite-type surface quasi-isometric to a graph of curves?
method Using the work of Rosendal, Mann, and Rafi, the study defines a necessary and sufficient condition called translatability for a mapping class group to be quasi-isometric to a graph of curves.
result The mapping class group of the plane minus a Cantor set is quasi-isometric to the loop graph defined by Bavard.
No natural topological compactification for Fulton-MacPherson.
problem Compactification of configuration spaces on topological manifolds.
method Using recent work on configuration spaces and compactifications.
result Fulton-MacPherson compactification cannot be extended topologically.
Common complex diseases are likely influenced by the interplay of hundreds, or even thousands, of genetic variants. Converging evidence shows that genetic variants with low marginal effects (LME) play an important role in disease development. Despite their potential significance, discovering LME genetic variants and as…
New method solves root-finding problems with faster convergence.
problem Finite-sum co-coercive equations
method Variance-reduced Krasnoselkii--Mann methods
result Achieves both and convergence rates
Historically tensor calculus emerged in an attempt to formalize Rie- mann's ideas. We show that tensor calculus can be based also on Lie's idea of a transformation group and this approach leads quite naturally to the concept of deformation of a transformation group and the Kodaira- Spencer map.
We calculate the integer cohomology ring and stable tangent bundle of a family of compact, 3-Sasakian 7-manifolds constructed by Boyer, Galicki, Mann, and Rees. Previously only the rational cohomology ring was known. The most important part of the cohomology ring is a torsion group that we describe explicitly and whose…
New analysis of stochastic approximation with non-expansive mappings.
problem Finite-time analysis of two-time-scale stochastic approximation with non-expansive mappings.
method Studied two-time-scale stochastic approximation algorithms with non-expansive mappings and projection steps.
result Last-iterate mean square residual error decays at a rate .
We consider the interplay of point counts, singular cohomology, étale cohomology, eigenvalues of the Frobenius and the Grothendieck ring of varieties for two families of varieties: spaces of rational maps and moduli spaces of marked, degree rational curves in . We deduce as special cases algebro-geome…
In this paper, we study Jacobi operators associated to algebraic curvature maps (tensors) on lightlike submanifolds M. We investigate conditions for an induced Rie- mann curvature tensor to be an algebraic curvature tensor on M. We introduce the notion of lightlike Osserman submanifolds and an example of 2-degenerate O…
Perfect mapping class groups of specific surfaces have no proper subgroups.
problem Characterizing the structure of mapping class groups of surfaces with removed Cantor sets.
method Automatic continuity of the groups, proven by Mann.
result These groups have no proper finite-index subgroups and trivial abelianization.
Classification of torus homeomorphisms on fine curve graph completed.
problem Classifying actions of torus homeomorphisms on fine curve graph.
method Proof involving slow rotation sets for torus homeomorphisms.
result Actions of torus homeomorphisms on fine curve graph classified.
Study shows surfaces without certain curves have infinite orbit graph.
problem Characterizing surfaces with specific curve properties.
method Utilized tools from mapping class group geometry.
result Infinite-invariance index 1 surfaces lack good curve graphs.
The spectral asymptotics for linear elasticity with mixed boundary conditions are shown to be old results.
problem Analyzing the spectral asymptotics for linear elasticity with mixed boundary conditions.
method Demonstrating that the results are essentially old well-known results by other authors.
result The spectral asymptotics results for linear elasticity with mixed boundary conditions are shown to be old results by other authors.
New proof classifies homogeneous 3-Sasakian and quaternionic Kähler manifolds.
problem Classifying homogeneous 3-Sasakian and quaternionic Kähler manifolds.
method Constructing an explicit one-to-one correspondence via root systems and analyzing properties of real projective spaces.
result Derivation of the classification of homogeneous positive quaternionic Kähler manifolds.
Classifies when homeomorphism groups of stable surfaces have automatic continuity.
problem Determining when homeomorphism groups of stable surfaces are continuous.
method Developed a general framework to prove automatic continuity for homeomorphism groups, applied to stable surfaces and Stone spaces.
result Classification of stable surfaces with respect to automatic continuity of their homeomorphism groups.
Study shows universal circle isomorphic to flow space ideal boundary.
problem Understanding foliations and pseudo-Anosov flows in 3-manifolds.
method Analyzing depth-one foliations and pseudo-Anosov flows in atoroidal 3-manifolds.
result Universal circle is isomorphic to flow space ideal boundary.
The study examines how perturbations of lattice actions on group boundaries behave.
problem Understanding how perturbations of lattice actions on group boundaries affect semi-conjugacy.
method Analyzes continuous factorization of perturbed actions onto original actions by semi-conjugacy.
result Perturbations of lattice actions on group boundaries can be semi-conjugate or not.
We present an objective function for learning with unlabeled data that utilizes auxiliary expectation constraints. We optimize this objective function using a procedure that alternates between information and moment projections. Our method provides an alternate interpretation of the posterior regularization framework (…
One- and two-sample nonparametric tests for the signal-to-noise ratio based on record statisticsstat.ME
A new family of nonparametric statistics, the r-statistics, is introduced. It consists of counting the number of records of the cumulative sum of the sample. The single-sample r-statistic is almost as powerful as Student's t-statistic for Gaussian and uniformly distributed variables, and more powerful than the sign and…
In hyperbolic L-spaces, we find multiple pseudo-Anosov flows with unique properties.
problem Finding multiple pseudo-Anosov flows in hyperbolic L-spaces.
method Used cylindrical contact homology and reconstruction of pseudo-Anosov flows from their closed orbits.
result Proved the existence of pseudo-Anosov flows in hyperbolic L-spaces, each with unique properties.
Simultaneous Laminationsmath.GT
Study of laminations for pseudo-Anosov flows on three-manifolds.
problem Understanding laminations for pseudo-Anosov flows on three-manifolds.
method Analyzing laminations for pseudo-Anosov orbit space universal circles, using prelaminations and results from Barthelmé, Bonatti, and Mann.
result Laminations and are completely determined by prelaminations on the boundary of the orbit space.
On the large scale geometry of big mapping class groups of surfaces with a unique maximal endmath.GT
Characterizes and analyzes the large scale geometry of big mapping class groups of surfaces.
problem Analyzing the large scale geometry of big mapping class groups of surfaces with a unique maximal end.
method Building on previous work, the paper characterizes and analyzes the large scale geometry of big mapping class groups of surfaces with a unique maximal end.
result Proves that any locally CB big mapping class group is CB generated and gives an explicit criterion for determining which big mapping class groups are CB generated.
A novel approach for unsupervised domain adaptation for neural networks is proposed. It relies on metric-based regularization of the learning process. The metric-based regularization aims at domain-invariant latent feature representations by means of maximizing the similarity between domain-specific activation distribu…
This paper shows how pseudo-Anosov flows represent stable Hamiltonian classes and limits the ways 3-manifolds can be obtained from knots.
problem Understanding the canonical representatives of stable Hamiltonian classes and their implications for 3-manifolds.
method Explains the analogy between pseudo-Anosov flows and stable Hamiltonian classes and generalizes an argument to limit the ways 3-manifolds can be obtained from knots.
result There are finitely many pseudo-Anosov flows admitting positive Birkhoff sections on any given rational homology 3-sphere, and any 3-manifold can be obtained in at most finitely many ways as surgery on a fibered hyperbolic knot in .
Proposes MCDE for estimating dependency in data streams.
problem Estimating dependency of variables in data streams is challenging.
method Monte Carlo Dependency Estimation (MCDE) framework.
result MWP dependency estimator shows superiority over state-of-the-art measures.
Study on homeomorphism groups of telescoping 2-manifolds showing strong distortion.
problem Characterizing the homeomorphism group of telescoping 2-manifolds.
method Introduced telescoping 2-manifolds, studied homeomorphism groups, and used commutator subgroup properties.
result Homeomorphism group of telescoping 2-manifolds is strongly distorted.
We record various properties of twisted Becker-Gottlieb transfer maps and study their multiplicative properties analogous to Becker-Gottlieb transfer. We show these twisted transfer maps factorise through Becker-Schultz-Mann-Miller-Miller transfer; some of these might be well known. We apply this to show that $BSO(2n+1…
Study on self-similar surfaces and their mapping class groups generated by involutions.
problem When do big mapping class groups of self-similar surfaces generated by involutions?
method Investigation of self-similar surfaces with self-similar ends, focusing on infinite and one maximal ends.
result For self-similar surfaces with infinite maximal ends, their mapping class groups are generated by involutions and are uniformly perfect.
Let be a smooth flow on a smooth manifold and be a smooth orbit preserving map. The following problem is studied: suppose that for every point of there exists a germ of a smooth function at such that near we have that . Can the functions be glued …
Study of mapping class groups on infinite graphs, focusing on their large-scale geometry.
problem Understanding the large-scale geometry of mapping class groups on infinite graphs.
method Using coarse geometry techniques, classify coarsely bounded groups and compute asymptotic dimension.
result Identify conditions for global and local coarsely bounded pure mapping class groups of infinite rank graphs.
Memory-augmented neural networks improve machine translation performance.
problem Improving machine translation accuracy and flexibility.
method Evaluation of Neural Turing Machines and Differentiable Neural Computers for machine translation tasks.
result Memory-augmented neural networks perform similarly to attentional encoders on Vietnamese to English tasks but have lower BLEU scores on Romanian to English tasks.
Simplified Milnor-Schwarz lemma for geometric group theory.
problem Conditions for orbit maps to be quasi-isometries.
method Succinct treatment and applications to non-Archimedean groups.
result Sharpened results on mapping class groups and quasi-isometry classification.
Develops a new fairness learning approach for multi-task regression models.
problem Fairness in multi-task regression models with biased datasets.
method Uses rank-based non-parametric independence test (Mann Whitney U statistic) and reformulates as non-convex optimization problem.
result Outperforms state-of-the-art methods on fairness metrics.
Characterizes braid group actions on R and mapping class group actions on S1.
problem Understanding the rigidity of braid group actions on R and mapping class group actions on S1.
method Using the space of left orderings of B_n, isolated points, and conjugacy action of B_n.
result Characterizes actions of B_n on R that produce translation numbers agreeing with the standard action.
Improved stochastic Halpern iteration for fixed-point approximation in normed spaces.
problem Approximating fixed-points of nonexpansive and contractive operators in normed finite-dimensional spaces.
method Stochastic Halpern iteration with minibatch, analyzing oracle complexity.
result Improved oracle complexity for nonexpansive operators, with a lower bound of .
Transfer learning improves sentiment classification using XR framework.
problem Lack of labeled data for deep learning.
method XR framework applied to transfer learning between related tasks, using expected label proportions.
result Improved performance on aspect-based sentiment classification.