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 model predicts neural network performance from early training epochs, incorporating architecture impact.
The practical usage of reinforcement learning agents is often bottlenecked by the duration of training time. To accelerate training, practitioners often turn to distributed reinforcement learning architectures to parallelize and accelerate the training process. However, modern methods for scalable reinforcement learnin…
This study presents a novel, deep, fully convolutional architecture which is optimized for the task of EEG-based neonatal seizure detection. Architectures of different depths were designed and tested; varying network depth impacts convolutional receptive fields and the corresponding learned feature complexity. Two deep…
ICON-OCnet solves optimal execution problems with neural networks and few examples.
This work explores how neural network architecture affects robustness to noisy labels.
Modern audio source separation techniques rely on optimizing sequence model architectures such as, 1D-CNNs, on mixture recordings to generalize well to unseen mixtures. Specifically, recent focus is on time-domain based architectures such as Wave-U-Net which exploit temporal context by extracting multi-scale features. …
Study on encoding neural architectures for NAS, showing impact on performance.
The term Neural Architecture Search (NAS) refers to the automatic optimization of network architectures for a new, previously unknown task. Since testing an architecture is computationally very expensive, many optimizers need days or even weeks to find suitable architectures. However, this search time can be significan…
Bayesian optimisation with graph kernels improves neural architecture search and provides interpretability.
Study shows refugee matching gains are robust to different evaluation methods.
Higher granularity in MoE models boosts expressivity exponentially.
In this paper we present a statistical analysis about the characteristics that we intend to influence in the performance of the neural networks in terms of assertiveness in the prediction of Brazilian stock returns. We created a population of architectures for analysis and extracted the sample that had the best asserti…
Neural Architecture Search (NAS) is an exciting new field which promises to be as much as a game-changer as Convolutional Neural Networks were in 2012. Despite many great works leading to substantial improvements on a variety of tasks, comparison between different methods is still very much an open issue. While most al…
Deep learning models reconstruct volatility surfaces from noisy data under no-arbitrage constraints.
With the success of deep neural networks, Neural Architecture Search (NAS) as a way of automatic model design has attracted wide attention. As training every child model from scratch is very time-consuming, recent works leverage weight-sharing to speed up the model evaluation procedure. These approaches greatly reduce …
Cell-based NAS search spaces are redundant and lack novelty.
A new UNet variant reduces spectral artifacts in image transformations.
We provide an overview of several non-linear activation functions in a neural network architecture that have proven successful in many machine learning applications. We conduct an empirical analysis on the effectiveness of using these function on the MNIST classification task, with the aim of clarifying which functions…
Framework ranks sectors influenced by Indian Union Budgets.
Paper analyzes soft tree ensembles using NTK, finding only leaf count matters.
A hybrid ASR system using conformer architecture improves word-error-rate and training speed.
New method improves neural architecture search by optimizing for both performance and diversity.
We introduce a mixed integer program (MIP) for assigning importance scores to each neuron in deep neural network architectures which is guided by the impact of their simultaneous pruning on the main learning task of the network. By carefully devising the objective function of the MIP, we drive the solver to minimize th…
Deep Echo State Networks (DeepESNs) recently extended the applicability of Reservoir Computing (RC) methods towards the field of deep learning. In this paper we study the impact of constrained reservoir topologies in the architectural design of deep reservoirs, through numerical experiments on several RC benchmarks. Th…
Paper introduces privacy-preserving deep-learning service.
Develops a new framework for integrating satellite allocations in small portfolios.
This paper investigates how network width and depth affect adversarially robust DNNs.
Bayesian Optimization (BO) is a common approach for hyperparameter optimization (HPO) in automated machine learning. Although it is well-accepted that HPO is crucial to obtain well-performing machine learning models, tuning BO's own hyperparameters is often neglected. In this paper, we empirically study the impact of o…
This study examines how model architecture affects deep learning model privacy.
Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. GPU hours) makes it difficult to \emph{directly} search the architectures on large-scale tasks (e.g. ImageNet).…
Theory explains why DARTS favors deep architectures over shallow ones.
NoisyDARTS injects random noise to improve neural architecture search.
Empirical study shows removing neural parameter symmetries impacts model performance.
Weight-sharing (WS) has recently emerged as a paradigm to accelerate the automated search for efficient neural architectures, a process dubbed Neural Architecture Search (NAS). Although very appealing, this framework is not without drawbacks and several works have started to question its capabilities on small hand-craf…
This paper distills Bayesian posterior expectations for deep neural networks.
Importance-weighted risk minimization is a key ingredient in many machine learning algorithms for causal inference, domain adaptation, class imbalance, and off-policy reinforcement learning. While the effect of importance weighting is well-characterized for low-capacity misspecified models, little is known about how it…
Study on shortcuts in deep networks, revealing their layer-wise distribution and impact.
Study evaluates scalability and real-world impact of disentangled representations.
Maintaining good cardiac function for as long as possible is a major concern for healthcare systems worldwide and there is much interest in learning more about the impact of different risk factors on cardiac health. The aim of this study is to analyze the impact of systolic blood pressure (SBP) on cardiac function whil…
This paper uses graph convolutional networks to improve the accuracy of neural architecture search.
This study analyzes NAS benchmarks and finds that only a subset of operations is crucial for generating high-performing architectures.
Most digital cameras use sensors coated with a Color Filter Array (CFA) to capture channel components at every pixel location, resulting in a mosaic image that does not contain pixel values in all channels. Current research on reconstructing these missing channels, also known as demosaicing, introduces many artifacts, …
This paper evaluates heuristics and hyperparameters in weight-sharing NAS methods.
Online retailers execute a very large number of price updates when compared to brick-and-mortar stores. Even a few mis-priced items can have a significant business impact and result in a loss of customer trust. Early detection of anomalies in an automated real-time fashion is an important part of such a pricing system.…
The presence of Long Distance Dependencies (LDDs) in sequential data poses significant challenges for computational models. Various recurrent neural architectures have been designed to mitigate this issue. In order to test these state-of-the-art architectures, there is growing need for rich benchmarking datasets. Howev…
Measures equivariance in vision models using Lie derivative.
Anisotropic data structure affects learning dynamics and generalization error in linear networks.
Reduced numerical precision is a common technique to reduce computational cost in many Deep Neural Networks (DNNs). While it has been observed that DNNs are resilient to small errors and noise, no general result exists that is capable of predicting a given DNN system architecture's sensitivity to reduced precision. In …