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.
New method selects inputs for Bayesian regression with few samples.
Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by learning to map a context set of observed input-output pairs to a distribution over regression functions. Each function models the distribution of the output given an input, conditioned on the context. NPs have the benefit of fitting observed data ef…
LESS combines local predictors for subsets to learn from heterogeneous input-output pairs.
JES optimizes expensive functions by considering joint entropy over input and output spaces.
Tensor completion method identifies nonlinear systems from input-output data.
This paper presents a method for solving the supervised learning problem in which the output is highly nonlinear and discontinuous. It is proposed to solve this problem in three stages: (i) cluster the pairs of input-output data points, resulting in a label for each point; (ii) classify the data, where the correspondin…
Recursive sketches summarize deep networks, aiding quick analysis and learning.
Convex optimization models predict outputs from inputs via optimization problems.
We consider the learning of algorithmic tasks by mere observation of input-output pairs. Rather than studying this as a black-box discrete regression problem with no assumption whatsoever on the input-output mapping, we concentrate on tasks that are amenable to the principle of divide and conquer, and study what are it…
Centroid Transformers reduce memory and computation by summarizing inputs into centroids.
New method learns functions without paired data using mediating variables.
Improved code translation by preserving structure with composed fine-tuning.
VAIOM models financial returns using continuous input and categorical output.
We introduce a novel loss function for training deep learning architectures to perform classification. It consists in minimizing the smoothness of label signals on similarity graphs built at the output of the architecture. Equivalently, it can be seen as maximizing the distances between the network function images of t…
Learning, taking into account full distribution of the data, referred to as generative, is not feasible with deep neural networks (DNNs) because they model only the conditional distribution of the outputs given the inputs. Current solutions are either based on joint probability models facing difficult estimation proble…
New recursive algorithm estimates conditional kernel mean embeddings in Hilbert space.
We present a probabilistic deep learning methodology that enables the construction of predictive data-driven surrogates for stochastic systems. Leveraging recent advances in variational inference with implicit distributions, we put forth a statistical inference framework that enables the end-to-end training of surrogat…
Starting from a dataset with input/output time series generated by multiple deterministic linear dynamical systems, this paper tackles the problem of automatically clustering these time series. We propose an extension to the so-called Martin cepstral distance, that allows to efficiently cluster these time series, and a…
Paper tackles blind polynomial regression for unknown inputs.
Despite tremendous progress in outlier detection research in recent years, the majority of existing methods are designed only to detect unconditional outliers that correspond to unusual data patterns expressed in the joint space of all data attributes. Such methods are not applicable when we seek to detect conditional …
We present a learning theory for the training of a linear system operator having an input compositional variable and propose a Bayesian inversion method for inferring the unknown variable from an output of a noisy linear system. We assume that we have partial or even no knowledge of the operator but have training data …
Entangled watermarks improve model defense against extraction attacks.
Paper introduces a novel method to generate diverse inputs for neural programming by example.
Physics-informed DeepONets solve PDEs without paired data, predicting solutions quickly.
A deep convolutional fuzzy system (DCFS) on a high-dimensional input space is a multi-layer connection of many low-dimensional fuzzy systems, where the input variables to the low-dimensional fuzzy systems are selected through a moving window across the input spaces of the layers. To design the DCFS based on input-outpu…
DiffDenoise preserves fine structures in medical images using conditional diffusion models.
Neural networks adapt to any input dimensionality.
Surrogate strategies are used widely for uncertainty quantification of groundwater models in order to improve computational efficiency. However, their application to dynamic multiphase flow problems is hindered by the curse of dimensionality, the saturation discontinuity due to capillarity effects, and the time-depende…
New sampling methods improve Shapley values for explaining machine learning predictions.
Quantifying similarity between data objects is an important part of modern data science. Deciding what similarity measure to use is very application dependent. In this paper, we combine insights from systems theory and machine learning, and investigate the weighted cepstral distance, which was previously defined for si…
A layered neural network is now one of the most common choices for the prediction of high-dimensional practical data sets, where the relationship between input and output data is complex and cannot be represented well by simple conventional models. Its effectiveness is shown in various tasks, however, the lack of inter…
Paper proposes a new ML approach to estimate g-vulnerability without estimating conditional probabilities.
DeepTrader learns to mimic a successful trader from market data.
Generative models improve image classifier explanations by realistically removing features.
Neural network learns atomic coordinates from Patterson maps in a simplified case.
We consider the problem of generating automatic code given sample input-output pairs. We train a neural network to map from the current state and the outputs to the program's next statement. The neural network optimizes multiple tasks concurrently: the next operation out of a set of high level commands, the operands of…
Develops structured noise for more accurate graph classifier robustness certificates.
TCNs can approximate complex input-output maps with limited memory.
We view molecular optimization as a graph-to-graph translation problem. The goal is to learn to map from one molecular graph to another with better properties based on an available corpus of paired molecules. Since molecules can be optimized in different ways, there are multiple viable translations for each input graph…
This paper tackles learning functions on manifolds using parallel distributed learning.
Pairwise Label Smoothing improves deep model generalization by reducing overconfidence.
A new method reduces both input and output dimensions for better goal-oriented analysis.
Machine learning qualifies computers to assimilate with data, without being solely programmed [1, 2]. Machine learning can be classified as supervised and unsupervised learning. In supervised learning, computers learn an objective that portrays an input to an output hinged on training input-output pairs [3]. Most effic…
Safe neural networks for input-output specifications.
The paper creates nonparametric confidence bands for band-limited functions.
A new method quantifies uncertainty in brain injury simulations.
Over-parameterized neural networks generalize well in practice without any explicit regularization. Although it has not been proven yet, empirical evidence suggests that implicit regularization plays a crucial role in deep learning and prevents the network from overfitting. In this work, we introduce the gradient gap d…
We analyze the problem of regression when both input covariates and output responses are functions from a nonparametric function class. Function to function regression (FFR) covers a large range of interesting applications including time-series prediction problems, and also more general tasks like studying a mapping be…