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 insights into neural network forgetting reveal a trade-off between node activation and re-use.
Model explains money creation under regulatory constraints.
Algorithm finds best mixture of training datasets for improved validation performance.
Traditional statistical theory assumes that the analysis to be performed on a given data set is selected independently of the data themselves. This assumption breaks downs when data are re-used across analyses and the analysis to be performed at a given stage depends on the results of earlier stages. Such dependency ca…
Mobile devices learn audio representations using self-supervised methods.
This paper introduces new attention-based convolutional neural networks for selecting bands from hyperspectral images. The proposed approach re-uses convolutional activations at different depths, identifying the most informative regions of the spectrum with the help of gating mechanisms. Our attention techniques are mo…
We present an embedding of stochastic optimal control problems, of the so called path integral form, into reproducing kernel Hilbert spaces. Using consistent, sample based estimates of the embedding leads to a model free, non-parametric approach for calculation of an approximate solution to the control problem. This fo…
One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature representation that satisfies a temporal constraint. We present an implementation…
In the present work we propose a Deep Feed Forward network architecture which can be trained according to a sequential learning paradigm, where tasks of increasing difficulty are learned sequentially, yet avoiding catastrophic forgetting. The proposed architecture can re-use the features learned on previous tasks in a …
We build new test sets for the CIFAR-10 and ImageNet datasets. Both benchmarks have been the focus of intense research for almost a decade, raising the danger of overfitting to excessively re-used test sets. By closely following the original dataset creation processes, we test to what extent current classification mode…
The paper proposes a method to transfer skills between tasks using disentangled latent policies.
We introduce the Mondrian kernel, a fast random feature approximation to the Laplace kernel. It is suitable for both batch and online learning, and admits a fast kernel-width-selection procedure as the random features can be re-used efficiently for all kernel widths. The features are constructed by sampling trees via a…
BayesFlow trains neural networks for fast Bayesian inference.
New framework boosts neural network performance and resilience.
New methods make Bayesian inference feasible for complex cognitive models.
We study the complexity of functions computable by deep feedforward neural networks with piecewise linear activations in terms of the symmetries and the number of linear regions that they have. Deep networks are able to sequentially map portions of each layer's input-space to the same output. In this way, deep models c…
We propose to prune a random forest (RF) for resource-constrained prediction. We first construct a RF and then prune it to optimize expected feature cost & accuracy. We pose pruning RFs as a novel 0-1 integer program with linear constraints that encourages feature re-use. We establish total unimodularity of the constra…
Study confirms eurozone interbank market stability but finds higher collateral reuse.
C-OPH improves One Permutation Hashing by using a shorter circulant permutation.
Dataset augmentation, the practice of applying a wide array of domain-specific transformations to synthetically expand a training set, is a standard tool in supervised learning. While effective in tasks such as visual recognition, the set of transformations must be carefully designed, implemented, and tested for every …
Stochastic Gradient Descent (SGD) is a workhorse in machine learning, yet its slow convergence can be a computational bottleneck. Variance reduction techniques such as SAG, SVRG and SAGA have been proposed to overcome this weakness, achieving linear convergence. However, these methods are either based on computations o…
Study evaluates how well question-answering models generalize to new data types.
Optimizes SGD for anytime neural networks, improving accuracy.
The study uses supervised learning to classify research data by discipline.
Study measures impact of data and neural net similarity on transferability in restaurant sales data.
We consider the problem of modelling noisy but highly symmetric shapes that can be viewed as hierarchies of whole-part relationships in which higher level objects are composed of transformed collections of lower level objects. To this end, we propose the stochastic wreath process, a fully generative probabilistic model…
We address the problem of Bayesian structure learning for domains with hundreds of variables by employing non-parametric bootstrap, recursively. We propose a method that covers both model averaging and model selection in the same framework. The proposed method deals with the main weakness of constraint-based learning--…
We study how network structure affects the dynamics of collateral in presence of rehypothecation. We build a simple model wherein banks interact via chains of repo contracts and use their proprietary collateral or re-use the collateral obtained by other banks via reverse repos. In this framework, we show that total col…
Two approaches extend knowledge distillation to Gaussian Processes, showing relationships to existing methods.
In this paper we consider two sequence tagging tasks for medieval Latin: part-of-speech tagging and lemmatization. These are both basic, yet foundational preprocessing steps in applications such as text re-use detection. Nevertheless, they are generally complicated by the considerable orthographic variation which is ty…
Bayesian approach sparsifies neural networks efficiently.
This work proposes splitting deep neural networks into smaller sub-networks for faster and more efficient distillation.
Efficiently models Wrong-Way Risk in FVA without full Monte Carlo.
In this paper, we present a novel approach for initializing deep neural networks, i.e., by turning PCA into neural layers. Usually, the initialization of the weights of a deep neural network is done in one of the three following ways: 1) with random values, 2) layer-wise, usually as Deep Belief Network or as auto-encod…
The effectiveness of Convolutional Neural Networks stems in large part from their ability to exploit the translation invariance that is inherent in many learning problems. Recently, it was shown that CNNs can exploit other invariances, such as rotation invariance, by using group convolutions instead of planar convoluti…
DeepClean detects and removes artefacts from ICU waveform data.
BERT models can classify multilingual party manifestos across different dimensions.
A new method compares image classifiers using adaptive sampling of natural images.
C-MinHash reduces the number of permutations needed for MinHash from thousands to just two.
The paper explores how agents can generalize to new environments with unseen variables.
New framework for modular reinforcement learning reduces sample complexity.
Agent learns diverse hierarchical structures in unknown environments.
In this paper, we focus on developing efficient sensitivity analysis methods for a computationally expensive objective function in the case that the minimization of it has just been performed. Here "computationally expensive" means that each of its evaluation takes significant amount of time, and therefore our m…
Framework uses diffusion models to infer material properties from noisy mechanical measurements.
The paper introduces sanity tests to detect spurious correlations in AI-guided radiology systems.
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia. The aim of this paper is to achieve ultra-high energy efficiency and performance for hardware implementations of deep neural networks (DNNs). An algorithm-hardware co-optimization framework is developed, which i…
Medical imaging machine learning algorithms are usually evaluated on a single dataset. Although training and testing are performed on different subsets of the dataset, models built on one study show limited capability to generalize to other studies. While database bias has been recognized as a serious problem in the co…
Two-layer networks learn faster with batch reuse, overcoming information and leap exponents.