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.
Gradient span algorithms show consistent progress in high dimensions.
A random walk on a separable, geodesic hyperbolic metric space converges to the boundary with probability one when the step distribution supports two independent loxodromics. In particular, the random walk makes positive linear progress. Progress is known to be linear with exponential decay when …
We show that a random walk on the mapping class group of an orientable surface of finite type makes linear progress in the relative metric, which is quasi-isometric to the complex of curves.
Wield simplifies reinforcement learning task design.
Efficient search methods can outperform random search on challenging tasks.
We develop an algorithm for systematic design of a large artificial neural network using a progression property. We find that some non-linear functions, such as the rectifier linear unit and its derivatives, hold the property. The systematic design addresses the choice of network size and regularization of parameters. …
We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial networks (GANs) are known for their ability to simulate random high-quality images, bu…
This paper explores the trade-off between spatial and adversarial robustness in neural networks.
New method learns optimal environment and goal difficulty for reinforcement learning.
This work designs an active world model learning system with progress-based curiosity.
The paper describes how martingales can be represented after a random time in financial models.
Survey on strong convergence in random matrices and its applications.
Drop-Muon updates only some layers, speeding up training.
Machine learning improves design verification, achieving better coverage than random methods.
The purpose of this paper is to give a selective survey on recent progress in random metric theory and its applications to conditional risk measures. This paper includes eight sections. Section 1 is a longer introduction, which gives a brief introduction to random metric theory, risk measures and conditional risk measu…
In clinical practice and biomedical research, measurements are often collected sparsely and irregularly in time while the data acquisition is expensive and inconvenient. Examples include measurements of spine bone mineral density, cancer growth through mammography or biopsy, a progression of defective vision, or assess…
Extracting a curriculum from a teacher network improves distillation efficiency.
Let G be a countable group which acts by isometries on a separable, but not necessarily proper, Gromov hyperbolic space X. We say the action of G is weakly hyperbolic if G contains two independent hyperbolic isometries. We show that a random walk on such G converges to the Gromov boundary almost surely. We apply the co…
Study on BSDEs with random time horizon, focusing on existence and properties.
Transformers improve Alzheimer's disease progression prediction by accounting for irregular biomarker histories.
AL2 progressively penalizes network activations to prevent overfitting.
New methods link Calabi-Yau metrics to random matrices.
A new principle for extrapolating regression outside training data.
In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress. In this work, we use a curriculum of progressively growing action spaces to accelerate learning. We assume the environment is out of our control, but that the agent …
High-dimensional statistics advances in complex data domains.
This paper completes the analysis of Choulli et al. Non-Arbitrage up to Random Horizons and after Honest Times for Semimartingale Models and contains two principal contributions. The first contribution consists in providing and analysing many practical examples of market models that admit classical arbitrages while the…
We study multiple defaults where the global market information is modelled as progressive enlargement of filtrations. We shall provide a general pricing formula by establishing a relationship between the enlarged filtration and the reference default-free filtration in the random measure framework. On each default scena…
A plethora of recent research has focused on improving the memory footprint and inference speed of deep networks by reducing the complexity of (i) numerical representations (for example, by deterministic or stochastic quantization) and (ii) arithmetic operations (for example, by binarization of weights). We propose a s…
Ensemble model predicts AD progression from CN status with high accuracy.
DrNAS improves neural architecture search with Dirichlet distribution and progressive learning.
Study on geodesics on random hyperbolic surfaces, showing variance asymptotic to X log X.
Fermat-Torricelli points help assess investment risks by smoothing series data.
New algorithms handle missing outcomes in MAB, reducing regret.
This paper addresses the question of how an arbitrage-free semimartingale model is affected when stopped at a random horizon. We focus on No-Unbounded-Profit-with-Bounded-Risk (called NUPBR hereafter) concept, which is also known in the literature as the first kind of non-arbitrage. For this non-arbitrage notion, we ob…
Sparse random networks reduce communication in federated learning.
This paper extends results of Mortimer and Williams (1991) about changes of probability measure up to a random time under the assumptions that all martingales are continuous and that the random time avoids stopping times. We consider locally absolutely continuous measure changes up to a random time, changes of probabil…
Purpose: Machine learning is broadly used for clinical data analysis. Before training a model, a machine learning algorithm must be selected. Also, the values of one or more model parameters termed hyper-parameters must be set. Selecting algorithms and hyper-parameter values requires advanced machine learning knowledge…
Randomized algorithms that base iteration-level decisions on samples from some pool are ubiquitous in machine learning and optimization. Examples include stochastic gradient descent and randomized coordinate descent. This paper makes progress at theoretically evaluating the difference in performance between sampling wi…
Map matching of GPS trajectories from a sequence of noisy observations serves the purpose of recovering the original routes in a road network. In this work in progress, we attempt to share our experience of feature construction in a spatial database by reporting our ongoing experiment of feature extrac-tion in Conditio…
The thesis presents a new perspective on high-dimensional optimization.
Study binary perceptrons' capacity using random duality theory.
The weights of a neural network are typically initialized at random, and one can think of the functions produced by such a network as having been generated by a prior over some function space. Studying random networks, then, is useful for a Bayesian understanding of the network evolution in early stages of training. In…
Random feature method approximates operators with theoretical guarantees and reduced computation.
In this article, we investigate when the set of primitive geodesic lengths on a Riemannian manifold have arbitrarily long arithmetic progressions. We prove that in the space of negatively curved metrics, a metric having such arithmetic progressions is quite rare. We introduce almost arithmetic progressions, a coarsific…
Paper proves a Central Limit Theorem for Random Forest Permutation Importance Measure.
Deep neural networks progressively transform their inputs across multiple processing layers. What are the geometrical properties of the representations learned by these networks? Here we study the intrinsic dimensionality (ID) of data-representations, i.e. the minimal number of parameters needed to describe a represent…
New methods tackle statistical inverse problems with random data.
Study uses Mean Field Game to analyze Bitcoin mining hashpower dynamics.