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.
A new risk budgeting scheme derived from universal portfolio theory.
HyperBO+ pre-trains a universal prior for Bayesian optimization across different domains.
Deep convolutional neural networks are known to specialize in distilling compact and robust prior from a large amount of data. We are interested in applying deep networks in the absence of training dataset. In this paper, we introduce deep audio prior (DAP) which leverages the structure of a network and the temporal in…
The Bayesian framework is a well-studied and successful framework for inductive reasoning, which includes hypothesis testing and confirmation, parameter estimation, sequence prediction, classification, and regression. But standard statistical guidelines for choosing the model class and prior are not always available or…
Transformer pretraining yields strong EB performance without explicit adaptation.
OptFormer learns universal HPO from diverse datasets.
Softmax attention approximates complex functions and subsumes many known universal approximators.
Neural-g models mixtures of densities with flexibility and accuracy.
Paper improves speech separation by using deep neural networks for more accurate density priors.
This work establishes universality for deep equivariant networks, overcoming limitations of previous approaches.
Proves identifiability of deep latent variable models without auxiliary information.
Identifying small subsets of features that are relevant for prediction and/or classification tasks is a central problem in machine learning and statistics. The feature selection task is especially important, and computationally difficult, for modern datasets where the number of features can be comparable to, or even ex…
This research formalizes uncertainty quantification for Universal Differential Equations models.
Transformers enable in-context learning with guarantees for a wide range of tasks.
Bayesian neural networks use ridgelet prior for uncertainty quantification.
Develops a new method for functional regression that works with non-Gaussian data.
We study the problem of learning classifiers robust to universal adversarial perturbations. While prior work approaches this problem via robust optimization, adversarial training, or input transformation, we instead phrase it as a two-player zero-sum game. In this new formulation, both players simultaneously play the s…
LDTA expands LDA's topic modeling capacity with tree-structured priors.
Model approximates market prices and returns without prior market dynamics.
Proposes PE-GP-UCB for time-varying Bayesian optimisation.
In this paper, we study two aspects of the variational autoencoder (VAE): the prior distribution over the latent variables and its corresponding posterior. First, we decompose the learning of VAEs into layerwise density estimation, and argue that having a flexible prior is beneficial to both sample generation and infer…
New method achieves both universality and adaptivity in online convex optimization.
PieClam autoencodes graphs into communities, improving graph anomaly detection.
Universal tester-learner for halfspaces over structured distributions.
Fast Bayesian inference with adaptable priors for real-time applications.
Introduces minimal surfaces to undergraduates.
Plug-and-play L-GM-AMP improves CS recovery for any i.i.d. source prior.
Bayesian algorithms perform well even with misspecified priors, especially in meta-learning.
o1Neuro neural network approximates complex functions and converges quickly.
Thurston's boundary to the universal Teichmüller space is the space of projective bounded measured laminations of . A geodesic ray in is of Teichmüller type if it shrinks vertical foliation of an integrable holomorphic quadratic differential. In a prio…
Probabilistic programming languages (PPLs) are powerful modelling tools which allow to formalise our knowledge about the world and reason about its inherent uncertainty. Inference methods used in PPL can be computationally costly due to significant time burden and/or storage requirements; or they can lack theoretical g…
New algorithm reduces regret in multi-armed bandit problems with Gaussian rewards.
Accelerating DNN execution on various resource-limited computing platforms has been a long-standing problem. Prior works utilize l1-based group lasso or dynamic regularization such as ADMM to perform structured pruning on DNN models to leverage the parallel computing architectures. However, both of the pruning dimensio…
New insights into model robustness for random features and NTK models.
This paper analyzes and improves GANs' approximation ability.
Develops a new method for online conformal prediction without manual tuning.
Universal probabilistic programming systems (PPSs) provide a powerful framework for specifying rich probabilistic models. They further attempt to automate the process of drawing inferences from these models, but doing this successfully is severely hampered by the wide range of non--standard models they can express. As …
Optimal transport offers an alternative to maximum likelihood for learning generative autoencoding models. We show that minimizing the p-Wasserstein distance between the generator and the true data distribution is equivalent to the unconstrained min-min optimization of the p-Wasserstein distance between the encoder agg…
We consider variational inequalities coming from monotone operators, a setting that includes convex minimization and convex-concave saddle-point problems. We assume an access to potentially noisy unbiased values of the monotone operators and assess convergence through a compatible gap function which corresponds to the …
Estimating symmetric properties of a distribution, e.g. support size, coverage, entropy, distance to uniformity, are among the most fundamental problems in algorithmic statistics. While each of these properties have been studied extensively and separate optimal estimators are known for each, in striking recent work, Ac…
New approach uses neural networks to learn program structure and parameters.
We introduce new definitions of universal and superuniversal computable codes, which are based on a code's ability to approximate Kolmogorov complexity within the prescribed margin for all individual sequences from a given set. Such sets of sequences may be singled out almost surely with respect to certain probability …
Inspired by the adaptation phenomenon of neuronal firing, we propose the regularity normalization (RN) as an unsupervised attention mechanism (UAM) which computes the statistical regularity in the implicit space of neural networks under the Minimum Description Length (MDL) principle. Treating the neural network optimiz…
Using an artificial neural network (ANN), a fixed universe of approximately 1500 equities from the Value Line index are rank-ordered by their predicted price changes over the next quarter. Inputs to the network consist only of the ten prior quarterly percentage changes in price and in earnings for each equity (by quart…
HardNet adds hard constraints to neural networks without sacrificing performance.
Prior distributions of binarized natural images are learned by using a Boltzmann machine. According the results of this study, there emerges a structure with two sublattices in the interactions, and the nearest-neighbor and next-nearest-neighbor interactions correspondingly take two discriminative values, which reflect…
In this paper, we present a novel way to summarize the structure of large graphs, based on non-parametric estimation of edge density in directed multigraphs. Following coclustering approach, we use a clustering of the vertices, with a piecewise constant estimation of the density of the edges across the clusters, and ad…
Nearest neighbor methods are a popular class of nonparametric estimators with several desirable properties, such as adaptivity to different distance scales in different regions of space. Prior work on convergence rates for nearest neighbor classification has not fully reflected these subtle properties. We analyze the b…