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.

168,657 papers · 148 categories

Trend · papers per month

3867731,1591,545 · Jun 202019922001200920172026
48 results for Cyclical Learning

This paper introduces 'General Cyclical Training' for neural networks.

problem Improving training efficiency and performance of neural networks.
method Cyclical training phases with varying hyperparameters, batch sizes, loss functions, and data augmentation.
result Cyclical weight decay, softmax temperature, and gradient clipping enhance model accuracy.

We solve structure learning for cyclic linear causal models using observational data.

problem Learning the structure of cyclic linear causal models from observational data.
method Assuming simple graphs, we use a criterion for distributional equivalence and implement a greedy search method.
result We show that simple cyclic models are of expected dimension and justify score-based methods for structure learning.

Cyclical MCMC tackles high-dimensional multimodal distributions, showing convergence under certain conditions.

problem High-dimensional multimodal posterior distributions in deep learning.
method Cyclical MCMC framework that tracks tempered versions of the target distribution over time.
result Cyclical MCMC converges to the target distribution under fast mixing kernels but fails in slow mixing cases.

MissNODAG learns cyclic causal graphs from incomplete data.

problem Causal discovery in systems with feedback loops and missing data.
method Differentiable framework integrating additive noise model and expectation-maximization.
result MissNODAG uncovers cyclic structures and missingness mechanisms from partially observed data.

Cyclic and randomized stepsizes can lead to heavier tails in SGD, improving generalization.

problem Understanding when and why cyclic and randomized stepsizes outperform constant stepsize in SGD.
method Examined a general class of Markovian stepsizes, focusing on their tail-index behavior.
result Markovian stepsizes can achieve heavier tails, improving generalization over constant stepsize.

The posteriors over neural network weights are high dimensional and multimodal. Each mode typically characterizes a meaningfully different representation of the data. We develop Cyclical Stochastic Gradient MCMC (SG-MCMC) to automatically explore such distributions. In particular, we propose a cyclical stepsize schedul…

2019-02-11abs ↗pdf ↗

We consider convex SGD updates with a block-cyclic structure, i.e. where each cycle consists of a small number of blocks, each with many samples from a possibly different, block-specific, distribution. This situation arises, e.g., in Federated Learning where the mobile devices available for updates at different times d…

2019-04-23abs ↗pdf ↗

New framework learns nonlinear cyclic causal models from data.

problem Challenges in learning causal relationships from real-world, cyclic systems.
method NODAGS-Flow: a novel framework using residual normalizing flows for likelihood estimation.
result Significant performance improvements in structure recovery and predictive performance compared to state-of-the-art methods.

CycleFQI tackles offline reinforcement learning for cyclic MDPs, mitigating state distribution mismatch.

problem Offline reinforcement learning for cyclic MDPs with heterogeneous dynamics and discount factors.
method CycleFQI decomposes the cyclic process into stage-wise sub-problems, using vector of stage-specific Q-functions.
result CycleFQI mitigates the curse of dimensionality and provides finite-sample suboptimality error bounds.

New cyclicity measures defined in weighted Besov spaces, with stability and geometric analysis.

problem Characterizing cyclicity in weighted Besov spaces.
method Defining cyclicity indices based on potential theory and capacity, studying stability under perturbations, and linking zero set structure to cyclicity.
result Novel invariants and conditions for cyclicity in various function spaces.

A new learning rule consistently reduces error over data samples.

problem Finding a learning rule that consistently reduces error over all data distributions.
method A deterministic, data-dependent partitioning rule that only partitions cyclic intervals with sufficient empirical diversity of labels.
result The expected error is monotone non-increasing with the sample size under every data distribution.

We refine the cyclic cohomological apparatus for computing the Hopf cyclic cohomology of the Hopf algebras associated to infinite primitive Cartan-Lie pseudogroups, and for the transfer of their characteristic classes to foliations. The main novel feature is the precise identification as a Hopf cyclic complex of the im…

2010-09-05abs ↗pdf ↗

Develop a variational framework for statistical inference on cyclic interactions.

problem Estimating and comparing large-scale recurrent organization in directed interactions.
method Represent directed interactions as edge flows on a simplicial complex and evolve under an energy-minimizing dynamical system.
result Separate transient interaction components from persistent harmonic flows, yielding a low-dimensional cycle space.

In this paper, we study quandles of cyclic type, which form a particular subclass of finite quandles. The main result of this paper describes the set of isomorphism classes of quandles of cyclic type in terms of certain cyclic permutations. By using our description, we give a direct classification of quandles of cyclic…

2013-12-25abs ↗pdf ↗

The paper investigates cyclic arbitrage opportunities in decentralized exchanges.

problem Price discrepancies in decentralized exchanges lead to arbitrage opportunities.
method Theoretical framework and analysis of transaction-level data.
result Traders have executed over 292,606 cyclic arbitrages over eleven months, exploiting more than 138 million USD in revenue.

In spin geometry, traceless cyclic homogeneous Riemannian manifolds equipped with a homogeneous spin structure can be viewed as the simplest manifolds after Riemannian symmetric spin spaces. In this paper, we give some characterizations and properties of cyclic and traceless cyclic homogeneous Riemannian manifolds and …

2014-07-21abs ↗pdf ↗

Study integrable discretizations of cyclic systems with circular coordinate lines.

problem Integrable discretizations of 3D cyclic systems with circular coordinate lines.
method Investigate circle congruences and flat connections in the context of discrete cyclic systems.
result Characterization of circle congruences and existence of certain flat connections.

A surgery on a knot in 3-sphere is called SU(2)-cyclic if it gives a manifold whose fundamental group has no non-cyclic SU(2) representations. Using holonomy perturbations on the Chern-Simons functional, we prove that the distance of two SU(2)-cyclic surgery coefficients is bounded by the sum of the absolute values of …

2013-06-29abs ↗pdf ↗

New definite 4-manifolds found with non-cyclic groups.

problem Finding exotic smooth structures on 4-manifolds with specific fundamental groups.
method Constructing infinitely many non-diffeomorphic structures.
result Infinitely many pairwise non-diffeomorphic definite 4-manifolds with Z/2imesZ/2\mathbb{Z}/2 imes \mathbb{Z}/2 fundamental group.

We classify SU(2)SU(2)-cyclic and SU(2)SU(2)-abelian 3-manifolds, for which every representation of the fundamental group into SU(2)SU(2) has cyclic or abelian image respectively, among geometric 3-manifolds which are not hyperbolic. As an application, we give examples of hyperbolic 3-manifolds which do not admit degree-1 maps …

2019-10-29abs ↗pdf ↗

Differential privacy is a useful tool to build machine learning models which do not release too much information about the training data. We study the Rényi differential privacy of stochastic gradient descent when each training example is sampled without replacement (also known as cyclic SGD). Cyclic SGD is typically f…

2019-07-11abs ↗pdf ↗

New framework for cyclic quantum causal models with graph separation property.

problem Understanding causal relationships in feedback processes and exotic scenarios.
method Introducing a robust probability rule and a novel graph-separation property, p-separation.
result Established graph-separation properties for all consistent cyclic causal models.

New Heegaard Floer homology for orbifolds with cyclic singularities.

problem Defining Heegaard Floer homology for orbifolds with arbitrary cyclic singularities.
method Generalizing recent work by defining Heegaard Floer homology for orbifolds with arbitrary cyclic singularities.
result Defined a new Heegaard Floer homology for orbifolds with arbitrary cyclic singularities.

A central result here is the computation of the entire cyclic homology of canonical smooth subalgebras of stable continuous trace C*-algebras having smooth manifolds M as their spectrum. More precisely, the entire cyclic homology is shown to be canonically isomorphic to the continuous periodic cyclic homology for these…

2004-12-24abs ↗pdf ↗

Let MM be an irreducible, compact, connected, orientable 3-manifold whose boundary is a torus. We show that if MM is hyperbolic, then it admits at most six finite/cyclic fillings of maximal distance 5. Further, the distance of a finite/cyclic filling to a cyclic filling is at most 2. If MM has a non-boundary-paralle…

1994-10-01abs ↗pdf ↗

We discuss 3-manifolds which are cyclic coverings of the 3-sphere, branched over 2-bridge knots and links. Different descriptions of these manifolds are presented: polyhedral, Heegaard diagram, Dehn surgery and coloured graph constructions. Using these descriptions, we give presentations for their fundamental groups, w…

2001-06-19abs ↗pdf ↗

The paper defines cyclic sets from ribbon string links and connects them to quantum invariants.

problem Defining and relating cyclic sets from ribbon string links.
method Endowing ribbon string links with cyclic and cocyclic structures, relating to coend of a ribbon category via quantum invariants.
result Established a relationship between ribbon string links and quantum invariants.

Develops Lie-theoretic perspective on Hitchin's equations for cyclic G-Higgs bundles.

problem Analytic and geometric properties of harmonic maps.
method Lie-theoretic perspective on Hitchin's equations for cyclic G-Higgs bundles.
result Proves Dai-Li's conjecture on the monotonicity of the energy density and negative curvature conjecture for Coxeter cyclic G-Higgs bundles.

We study tori which are cyclic covers of the standard torus, that is, the deck transformation group of the covering map is cyclic. These covering tori can be parametrized in a natural way and we show that being cyclic is equivalent to certain arithmetic condition on these parameters. There is a natural $\mathrm{SL}(2,\…

2015-06-09abs ↗pdf ↗

New examples show transverse knots are determined by their branched covers.

problem Transverse knots and their isotopy classes.
method Constructing and analyzing non-isotopic transverse knots with contactomorphic cyclic branched covers.
result Transverse isotopy classes of many transverse knots are determined by the contactomorphism type of their cyclic branched covers.