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.
The study finds necessary and sufficient conditions for -hypersurfaces to have nowhere -regular parallel sets.
A scalable parallel BO method for asynchronous settings.
Introduces a natural parallel translation for navigation data.
Characterizes regular parallelisms in 3D space with 2-torus action.
We suggest a general oracle-based framework that captures different parallel stochastic optimization settings described by a dependency graph, and derive generic lower bounds in terms of this graph. We then use the framework and derive lower bounds for several specific parallel optimization settings, including delayed …
Study on BAS manifolds with parallel torsion and curvature.
A concise discussion of the axiomatic approach to the concept of parallel transport is presented. Attention is drawn to a bijective map between the sets of connections and (axiomatically defined) parallel transports. The transports along paths are pointed as a generalization of the (axiomatically defined) parallel tran…
In this paper we consider planar polygons with parallel opposite sides. This type of polygons can be regarded as discretizations of closed convex planar curves by taking tangent lines at samples with pairwise parallel tangents. For this class of polygons, we define discrete versions of the area evolute, central symmetr…
The axiomatic approach to parallel transport theory is partially discussed. Bijective correspondences between the sets of connections, (axiomatically defined) parallel transports, and transports along paths satisfying some additional conditions, are constructed. In particular, the equivalence between the concepts "conn…
A single policy suffices for near-optimal parallel exploration in RL.
New algorithms improve causal direction inference accuracy using parallel ensemble methods.
We design and analyse variations of the classical Thompson sampling (TS) procedure for Bayesian optimisation (BO) in settings where function evaluations are expensive, but can be performed in parallel. Our theoretical analysis shows that a direct application of the sequential Thompson sampling algorithm in either synch…
The paper introduces a new method to measure the shape relations between biological objects using r-parallel sets.
Theory of parallel transport on non-collapsed RCD spaces established.
AgEBO-Tabular combines NAS and hyperparameter tuning for fast, high-performing tabular models.
Parallel transport in a fibre bundle with respect to smooth paths in the base space B have recently been extended to representations of the smooth singular simplicial set Sing_{smooth}(B). Inspired by these extensions,I revisit the development of a notion of `parallel' transport in the topological setting of fibrations…
Due to the escalating growth of big data sets in recent years, new Bayesian Markov chain Monte Carlo (MCMC) parallel computing methods have been developed. These methods partition large data sets by observations into subsets. However, for Bayesian nested hierarchical models, typically only a few parameters are common f…
We study the question of whether parallelization in the exploration of the feasible set can be used to speed up convex optimization, in the local oracle model of computation. We show that the answer is negative for both deterministic and randomized algorithms applied to essentially any of the interesting geometries and…
We consider non-degenerate centro-affine hypersurface immersions in R^n whose cubic form is parallel with respect to the Levi-Civita connection of the affine metric. There exists a bijective correspondence between homothetic families of proper affine hyperspheres with center in the origin and with parallel cubic form, …
Study of symmetric affine surfaces with non-vanishing torsion.
New BO methods exploit parallel experiments, reducing search time and improving solution quality.
The paper examines parallel one forms on Riemannian and Finslerian manifolds.
In a context of document co-clustering, we define a new similarity measure which iteratively computes similarity while combining fuzzy sets in a three-partite graph. The fuzzy triadic similarity (FT-Sim) model can deal with uncertainty offers by the fuzzy sets. Moreover, with the development of the Web and the high ava…
PHS optimizes hyperparameters in parallel for expensive computations.
MixML unifies analysis of weakly consistent parallel learning.
Parallelized bandit algorithms speed up decision-making.
Chemical space is so large that brute force searches for new interesting molecules are infeasible. High-throughput virtual screening via computer cluster simulations can speed up the discovery process by collecting very large amounts of data in parallel, e.g., up to hundreds or thousands of parallel measurements. Bayes…
We consider learning problems over training sets in which both, the number of training examples and the dimension of the feature vectors, are large. To solve these problems we propose the random parallel stochastic algorithm (RAPSA). We call the algorithm random parallel because it utilizes multiple parallel processors…
Method predicts how probability distributions evolve over time.
As is well known, a metric on a manifold determines a unique symmetric connection for which the metric is parallel: the Levi-Civita connection. In this paper we investigate the inverse problem: to what extent is the metric of a Riemannian manifold determined by its Levi-Civita connection? It is shown that for a generic…
TensorOpt finds optimal parallelization strategies for DNN training.
We show that given a conformal structure whose holonomy representation fixes a totally lightlike subspace of arbitrary dimension, there is always a local metric in the conformal class off a singular set which is Ricci-isotropic and gives rise to a parallel, totally lightlike distribution on the tangent bundle. This nat…
Study on charged parallel spinors and mass-charge inequalities.
Modern learning models are characterized by large hyperparameter spaces and long training times. These properties, coupled with the rise of parallel computing and the growing demand to productionize machine learning workloads, motivate the need to develop mature hyperparameter optimization functionality in distributed …
Proposes a new PBO method with theoretical guarantees.
MindFlayer SGD improves parallel SGD for heterogeneous, random compute times.
We consider parallel asynchronous Markov Chain Monte Carlo (MCMC) sampling for problems where we can leverage (stochastic) gradients to define continuous dynamics which explore the target distribution. We outline a solution strategy for this setting based on stochastic gradient Hamiltonian Monte Carlo sampling (SGHMC) …
Study nearly parallel G2-structures with torus symmetry using multi-moment maps.
Parallelizes feedforward computation using nonlinear equation solving.
Study the effects of data parallelism and sparsity on neural network training.
To scale non-parametric extensions of probabilistic topic models such as Latent Dirichlet allocation to larger data sets, practitioners rely increasingly on parallel and distributed systems. In this work, we study data-parallel training for the hierarchical Dirichlet process (HDP) topic model. Based upon a representati…
Sequential coordinate ascent is more robust in high-dimensional linear regression.
PETRA enables parallel training of deep models with reversible architectures.
The paper proves a global geometric formula for volume holonomy in gauge theory.
Adaptive quantization improves SGD accuracy in data-parallel settings.
We develop a parallel variational inference (VI) procedure for use in data-distributed settings, where each machine only has access to a subset of data and runs VI independently, without communicating with other machines. This type of "embarrassingly parallel" procedure has recently been developed for MCMC inference al…
An infinite parallel tempering bouncy particle sampler improves sampling efficiency for multimodal distributions.
In AI research and industry, machine learning is the most widely used tool. One of the most important machine learning algorithms is Gradient Boosting Decision Tree, i.e. GBDT whose training process needs considerable computational resources and time. To shorten GBDT training time, many works tried to apply GBDT on Par…