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.
Transformers learn to adapt to different task difficulties and resist distribution shifts.
Researchers calculated EVaR for various distributions using Lambert function.
This paper analyzes the difficulty of unsupervised domain adaptation using information theory.
Despite the significant advances in recent years, Generative Adversarial Networks (GANs) are still notoriously hard to train. In this paper, we propose three novel curriculum learning strategies for training GANs. All strategies are first based on ranking the training images by their difficulty scores, which are estima…
A pivotal problem in Bayesian nonparametrics is the construction of prior distributions on the space M(V) of probability measures on a given domain V. In principle, such distributions on the infinite-dimensional space M(V) can be constructed from their finite-dimensional marginals---the most prominent example being the…
The paper explores when to prioritize easy or hard samples in learning tasks.
Learning shrinks hard tail, improving inference performance.
Paper develops neural network for distribution regression.
Two-sample feature selection is the problem of finding features that describe a difference between two probability distributions, which is a ubiquitous problem in both scientific and engineering studies. However, existing methods have limited applicability because of their restrictive assumptions on data distributoins …
We investigate and compare the fundamental performance of several distributed learning methods that have been proposed recently. We do this in the context of a distributed version of the classical signal-in-Gaussian-white-noise model, which serves as a benchmark model for studying performance in this setting. The resul…
Study reveals differences in label shift problem difficulty in supervised vs. unsupervised settings.
We focus on the distribution regression problem: regressing to a real-valued response from a probability distribution. Although there exist a large number of similarity measures between distributions, very little is known about their generalization performance in specific learning tasks. Learning problems formulated on…
Proposes a context-aware approach to deep autoencoder novelty detection.
New algorithms handle heavy-tailed rewards in reinforcement learning.
The problem of categorical data analysis in high dimensions is considered. A discussion of the fundamental difficulties of probability modeling is provided, and a solution to the derivation of high dimensional probability distributions based on Bayesian learning of clique tree decomposition is presented. The main contr…
Score matching is a popular method for estimating unnormalized statistical models. However, it has been so far limited to simple, shallow models or low-dimensional data, due to the difficulty of computing the Hessian of log-density functions. We show this difficulty can be mitigated by projecting the scores onto random…
We tackle unsupervised anomaly detection (UAD), a problem of detecting data that significantly differ from normal data. UAD is typically solved by using density estimation. Recently, deep neural network (DNN)-based density estimators, such as Normalizing Flows, have been attracting attention. However, one of their draw…
This work sets theoretical limits on meta-learning performance.
Mathematical Reinforcement Learning faces a 'Two-Hump' problem due to sparse rewards and a scarcity of intermediate 'hard-but-solvable' instances.
Time-continuous emotion prediction has become an increasingly compelling task in machine learning. Considerable efforts have been made to advance the performance of these systems. Nonetheless, the main focus has been the development of more sophisticated models and the incorporation of different expressive modalities (…
In this paper, we propose a data collaboration analysis method for distributed datasets. The proposed method is a centralized machine learning while training datasets and models remain distributed over some institutions. Recently, data became large and distributed with decreasing costs of data collection. If we can cen…
D-Wave computers struggle with sampling Boltzmann distributions efficiently.
In the original version of the Variational Autoencoder, Kingma et al. assume Gaussian distributions for the approximate posterior during the inference and for the output during the generative process. This assumptions are good for computational reasons, e.g. we can easily optimize the parameters of a neural network usi…
CLOPS improves deep learning for continuous physiological data.
Deep networks prioritize easier examples over harder ones, leading to faster training.
TTF improves performance of normalizing flows for heavy-tailed distributions.
This work embeds annotations into a multidimensional space to measure classification difficulty.
VLM judges rank well but score poorly; task difficulty and annotation quality affect interval width.
GANs struggle with density estimation on simple datasets, while normalizing flows perform well.
This work builds the connection between the regularity theory of optimal transportation map, Monge-Ampère equation and GANs, which gives a theoretic understanding of the major drawbacks of GANs: convergence difficulty and mode collapse. According to the regularity theory of Monge-Ampère equation, if the support of the …
Paper defines a new distance metric for comparing learning tasks.
Paper benchmarks mutual info estimators on diverse distributions.
Some statistical models are specified via a data generating process for which the likelihood function cannot be computed in closed form. Standard likelihood-based inference is then not feasible but the model parameters can be inferred by finding the values which yield simulated data that resemble the observed data. Thi…
The paper develops a theory for iterative self-improvement of models, proving conditions for better performance with easy-to-hard curricula.
Entity Linking (EL) is the task of automatically identifying entity mentions in a piece of text and resolving them to a corresponding entity in a reference knowledge base like Wikipedia. There is a large number of EL tools available for different types of documents and domains, yet EL remains a challenging task where t…
New learning rule simplifies Bayesian updates for deep learning.
New distributed EnKF method for non-sequential assimilation of large datasets.
New measure quantifies task difficulty for machine learning models.
Flow based models such as Real NVP are an extremely powerful approach to density estimation. However, existing flow based models are restricted to transforming continuous densities over a continuous input space into similarly continuous distributions over continuous latent variables. This makes them poorly suited for m…
New ensemble models classify mouse movement trajectories to assess survey question difficulty.
The economic crisis in Argentina around year 2002 provides a unique opportunity for Econophysics studies. The available data on individual income are analyzed to show that they correspond to non stationary states. However, the rather restricted size of the data survey imposes difficulties that must be overcome through …
Paper designs a bandit algorithm without reward distribution info.
SGLD proves geometric ergodicity via reflection coupling for nonconvex log-concave distributions.
This paper applies secure multi-party computation to K-means clustering to protect private data.
This study links blockchain design to cryptos' distributional characteristics.
Boltzmann machines are undirected graphical models with two-state stochastic variables, in which the logarithms of the clique potentials are quadratic functions of the node states. They have been widely studied in the neural computing literature, although their practical applicability has been limited by the difficulty…
There has been an explosion of interest in statistical models for analyzing network data, and considerable interest in the class of exponential random graph (ERG) models, especially in connection with difficulties in computing maximum likelihood estimates. The issues associated with these difficulties relate to the bro…
Improves NF for complex data distributions with multiple modes.