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.
Stochastic approach improves neural network training for kinetic simulations.
To backpropagate the gradients through stochastic binary layers, we propose the augment-REINFORCE-merge (ARM) estimator that is unbiased, exhibits low variance, and has low computational complexity. Exploiting variable augmentation, REINFORCE, and reparameterization, the ARM estimator achieves adaptive variance reducti…
Study examines how data augmentation impacts optimization in linear regression.
Proposes a new framework for learning image augmentations to improve classification performance.
Stochastic neural ODEs outperform deterministic ones on image classification tasks.
SBA improves neural network generalization by dynamically augmenting data.
AugMask trains diffusion models on incomplete tabular data by augmenting missing values and applying denoising supervision.
Much of the data being created on the web contains interactions between users and items. Stochastic blockmodels, and other methods for community detection and clustering of bipartite graphs, can infer latent user communities and latent item clusters from this interaction data. These methods, however, typically ignore t…
New algorithm solves stochastic optimization problems with unknown gradients.
Develops a statistical framework for self-supervised representation learning using data augmentation.
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show that a potential-based reward shaping scheme is able to preserve optimality of stochastic policies, and demonstrate that the ability of an a…
Deep Learning (DL) methods have emerged as one of the most powerful tools for functional approximation and prediction. While the representation properties of DL have been well studied, uncertainty quantification remains challenging and largely unexplored. Data augmentation techniques are a natural approach to provide u…
A method to prevent image representation collapse through data-dependent augmentation.
This work improves neural likelihood surrogates for stochastic models with a score-augmented loss.
The generation of artificial data based on existing observations, known as data augmentation, is a technique used in machine learning to improve model accuracy, generalisation, and to control overfitting. Augmentor is a software package, available in both Python and Julia versions, that provides a high level API for th…
We introduce a simple and effective method for regularizing large convolutional neural networks. We replace the conventional deterministic pooling operations with a stochastic procedure, randomly picking the activation within each pooling region according to a multinomial distribution, given by the activities within th…
Categorical distributions are ubiquitous in machine learning, e.g., in classification, language models, and recommendation systems. However, when the number of possible outcomes is very large, using categorical distributions becomes computationally expensive, as the complexity scales linearly with the number of outcome…
New method speeds up inference for non-conjugate Gaussian processes.
Augmented bridge matching preserves coupling information between distributions.
New method learns dynamics from sparse data using geometric constraints.
SymDiff uses stochastic symmetrisation for equivariant diffusion models.
FSGD uses latent factors to scale SGD for high-dimensional learning.
The stochastic block model (SBM) is a probabilistic model for community structure in networks. Typically, only the adjacency matrix is used to perform SBM parameter inference. In this paper, we consider circumstances in which nodes have an associated vector of continuous attributes that are also used to learn the node-…
New algorithm tackles stochastic optimization with inequality constraints.
Paper proposes distributed optimization for federated learning with theoretical guarantees.
We propose a scalable stochastic variational approach to GP classification building on Polya-Gamma data augmentation and inducing points. Unlike former approaches, we obtain closed-form updates based on natural gradients that lead to efficient optimization. We evaluate the algorithm on real-world datasets containing up…
New algorithms reduce complexity for solving nonconvex optimization problems with stochastic objectives and constraints.
Exemplar VAEs link generative models with nearest neighbor retrieval and data augmentation.
We develop a general variational inference method that preserves dependency among the latent variables. Our method uses copulas to augment the families of distributions used in mean-field and structured approximations. Copulas model the dependency that is not captured by the original variational distribution, and thus …
Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency. In this work, we propose Augment-Reinforce-Merge (ARM) policy gradient estimator as an unbiased low-variance alternative to previous baseline estimators on tasks with binary action space, inspired by …
The paper provides theoretical guarantees for behavior cloning using generative models.
Proposes MR-SNE for multimodal data visualization.
Unified framework for generating synthetic financial time series that accurately capture both marginal distributions and temporal dynamics.
Probabilistic STNs improve image classification and robustness.
Stochastic optimization algorithms with variance reduction have proven successful for minimizing large finite sums of functions. Unfortunately, these techniques are unable to deal with stochastic perturbations of input data, induced for example by data augmentation. In such cases, the objective is no longer a finite su…
The problem of combined state and input estimation of linear structural systems based on measured responses and a priori knowledge of structural model is considered. A novel methodology using Gaussian process latent force models is proposed to tackle the problem in a stochastic setting. Gaussian process latent force mo…
We present a stochastic setting for optimization problems with nonsmooth convex separable objective functions over linear equality constraints. To solve such problems, we propose a stochastic Alternating Direction Method of Multipliers (ADMM) algorithm. Our algorithm applies to a more general class of nonsmooth convex …
We consider the stochastic nested composition optimization problem where the objective is a composition of two expected-value functions. We proposed the stochastic ADMM to solve this complicated objective. In order to find an stationary point where the expected norm of the subgradient of corresponding augmented Lag…
Paper solves optimization problems with convex expectation constraints using a new algorithm.
Boomerang generates nonidentical images similar to input on image manifolds.
A novel fully asynchronous scheme for distributed reinforcement learning over networks.
This work studies the valuation of currency options in markets suffering from a financial crisis. We consider a European option where the underlying asset is a foreign currency. We assume that the value of the underlying asset is a stochastic process that follows a modified Black-Scholes model with an augmented stochas…
This article is an overview of supervised machine learning problems for regression and classification. Topics include: kernel methods, training by stochastic gradient descent, deep learning architecture, losses for classification, statistical learning theory, and dimension independent generalization bounds. Implicit re…
A machine learning framework predicts self-induced stochastic resonance in neurons.
DHOG improves unsupervised clustering accuracy on image benchmarks.
Enhanced volatility forecasting using options data and rough volatility model.
It is challenging to develop stochastic gradient based scalable inference for deep discrete latent variable models (LVMs), due to the difficulties in not only computing the gradients, but also adapting the step sizes to different latent factors and hidden layers. For the Poisson gamma belief network (PGBN), a recently …
Standard results in stochastic convex optimization bound the number of samples that an algorithm needs to generate a point with small function value in expectation. More nuanced high probability guarantees are rare, and typically either rely on "light-tail" noise assumptions or exhibit worse sample complexity. In this …