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.
Classifies when homeomorphism groups of stable surfaces have automatic continuity.
Structured weight pruning is a representative model compression technique of DNNs to reduce the storage and computation requirements and accelerate inference. An automatic hyperparameter determination process is necessary due to the large number of flexible hyperparameters. This work proposes AutoCompress, an automatic…
Correctly identifying sleep stages is important in diagnosing and treating sleep disorders. This work proposes a joint classification-and-prediction framework based on CNNs for automatic sleep staging, and, subsequently, introduces a simple yet efficient CNN architecture to power the framework. Given a single input epo…
A new optimisation framework for neural networks without hyperparameters.
AutoKE automates embedding physical knowledge into neural networks for complex engineering problems.
Functional tensors unify probabilistic programming with automatic differentiation.
AdaNet is a lightweight TensorFlow-based (Abadi et al., 2015) framework for automatically learning high-quality ensembles with minimal expert intervention. Our framework is inspired by the AdaNet algorithm (Cortes et al., 2017) which learns the structure of a neural network as an ensemble of subnetworks. We designed it…
In this technical report I present my method for automatic synthetic dataset generation for object detection and demonstrate it on the video game League of Legends. This report furthermore serves as a handbook on how to automatically generate datasets and as an introduction on the dataset generation part of the LeagueA…
Background: Parkinson's disease (PD) is a prevalent long-term neurodegenerative disease. Though the diagnostic criteria of PD are relatively well defined, the current medical imaging diagnostic procedures are expertise-demanding, and thus call for a higher-integrated AI-based diagnostic algorithm. Methods: In this pape…
In deep learning, performance is strongly affected by the choice of architecture and hyperparameters. While there has been extensive work on automatic hyperparameter optimization for simple spaces, complex spaces such as the space of deep architectures remain largely unexplored. As a result, the choice of architecture …
Variational inference is a scalable technique for approximate Bayesian inference. Deriving variational inference algorithms requires tedious model-specific calculations; this makes it difficult to automate. We propose an automatic variational inference algorithm, automatic differentiation variational inference (ADVI). …
Deep learning detects schools of herring from echograms.
A framework assesses the quality of crowdsourced weather data.
agtboost speeds up gradient tree boosting with automatic complexity adjustment.
Machine learning speeds up GPR simulations.
Geometric AD framework simplifies derivative computation in JAX.
In this paper, a neural architecture search (NAS) framework is proposed for 3D medical image segmentation, to automatically optimize a neural architecture from a large design space. Our NAS framework searches the structure of each layer including neural connectivities and operation types in both of the encoder and deco…
In the classic sparsity-driven problems, the fundamental L-1 penalty method has been shown to have good performance in reconstructing signals for a wide range of problems. However this performance relies on a good choice of penalty weight which is often found from empirical experiments. We propose an algorithm called t…
Paper proposes NNAFC for automatic financial factor construction.
A new method, InfoGuide, improves automatic clustering analysis.
Python package automates causal parameter estimation using Riesz regression.
Paper presents a Transformer model for automatic domain adaptation.
Bayesian nonparametric models, such as Gaussian processes, provide a compelling framework for automatic statistical modelling: these models have a high degree of flexibility, and automatically calibrated complexity. However, automating human expertise remains elusive; for example, Gaussian processes with standard kerne…
Storchastic improves stochastic AD for complex models in RL and VI.
We present a model that can automatically learn alignments between high-dimensional data in an unsupervised manner. Our proposed method casts alignment learning in a framework where both alignment and data are modelled simultaneously. Further, we automatically infer groupings of different types of sequences within the …
Unified framework for automatic debiased machine learning for various statistical parameters.
ADIGen: Automatic, Debiased, and Invariant Counterfactual Generation
Specifying utility functions is a key step towards applying the discrete choice framework for understanding the behaviour processes that govern user choices. However, identifying the utility function specifications that best model and explain the observed choices can be a very challenging and time-consuming task. This …
AutoBayes simplifies variational inference by composing models and optimizing them.
ARDA automatically augments datasets for machine learning models.
Anomaly-aware forecast improves accuracy for extreme events.
SAFE automates feature engineering for industrial tasks efficiently and scalably.
PID control architectures are widely used in industrial applications. Despite their low number of open parameters, tuning multiple, coupled PID controllers can become tedious in practice. In this paper, we extend PILCO, a model-based policy search framework, to automatically tune multivariate PID controllers purely bas…
New method recovers compressed crack images for automatic segmentation.
Convolutional neural networks (CNNs) are effective at solving difficult problems like visual recognition, speech recognition and natural language processing. However, performance gain comes at the cost of laborious trial-and-error in designing deeper CNN architectures. In this paper, a genetic programming (GP) framewor…
Develops panoramic gastroscopy for automatic polyp detection.
BackPACK extends PyTorch to compute additional gradient info.
Automates perturbation analysis for neural networks, enabling certified robustness on complex architectures.
In likelihood-free settings where likelihood evaluations are intractable, approximate Bayesian computation (ABC) addresses the formidable inference task to discover plausible parameters of simulation programs that explain the observations. However, they demand large quantities of simulation calls. Critically, hyperpara…
HyperImpute improves iterative imputation by automatically selecting models and hyperparameters.
While great progress has been made recently in automatic image manipulation, it has been limited to object centric images like faces or structured scene datasets. In this work, we take a step towards general scene-level image editing by developing an automatic interaction-free object removal model. Our model learns to …
A new framework for systematic graph neural network data augmentation.
Bayesian TNKMs automatically infer model complexity and feature relevance.
AeGAN improves speech clarity in noisy environments.
A two-stage GPR framework with automatic kernel search and subsampling improves prediction accuracy and efficiency.
CoLA automates efficient numerical linear algebra for complex matrix structures.
Automated framework forecasts correlated time series in minutes.
The need to efficiently calculate first- and higher-order derivatives of increasingly complex models expressed in Python has stressed or exceeded the capabilities of available tools. In this work, we explore techniques from the field of automatic differentiation (AD) that can give researchers expressive power, performa…