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.
Approach generates multiple correct predictions from single supervision.
Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning representations with unlabeled datasets, i.e., learning without any human-annotated supervision. In this paper, we show that such a technique can be used to sign…
Current Flash X-ray single-particle diffraction Imaging (FXI) experiments, which operate on modern X-ray Free Electron Lasers (XFELs), can record millions of interpretable diffraction patterns from individual biomolecules per day. Due to the stochastic nature of the XFELs, those patterns will to a varying degree includ…
Self-supervised VAEs improve data compression and generation.
CoDATS improves DA on time series data with weak supervision.
New method improves image denoising with fewer parameters and less data.
Super-OT combines GANs and optimal transport for lineage tracing.
Minimalist softmax attention learns constrained Boolean functions with supervision.
In supervised clustering, standard techniques for learning a pairwise dissimilarity function often suffer from a discrepancy between the training and clustering objectives, leading to poor cluster quality. Rectifying this discrepancy necessitates matching the procedure for training the dissimilarity function to the clu…
McCullagh and Yang (2006) suggest a family of classification algorithms based on Cox processes. We further investigate the log Gaussian variant which has a number of appealing properties. Conditioned on the covariates, the distribution over labels is given by a type of conditional Markov random field. In the supervised…
Study investigates one-shot semi-supervised learning for image classification.
Deep semi-supervised learning identifies tree species from natural images.
We propose a new framework for single-channel source separation that lies between the fully supervised and unsupervised setting. Instead of supervision, we provide input features for each source signal and use convex methods to estimate the correlations between these features and the unobserved signal decomposition. We…
Unified framework for semi-supervised learning reduces annotation needs.
A new methodology for incorporating LGD correlation effects into the Basel II risk weight functions is introduced. This methodology is based on modelling of LGD and default event with a single loss variable. The resulting formulas for capital charges are numerically compared to the current proposals by the Basel Commit…
In structured prediction problems where we have indirect supervision of the output, maximum marginal likelihood faces two computational obstacles: non-convexity of the objective and intractability of even a single gradient computation. In this paper, we bypass both obstacles for a class of what we call linear indirectl…
Survey on self-supervised pre-training for neural networks using unlabeled data.
We study the problem of semi-supervised singing voice separation, in which the training data contains a set of samples of mixed music (singing and instrumental) and an unmatched set of instrumental music. Our solution employs a single mapping function g, which, applied to a mixed sample, recovers the underlying instrum…
New method learns to weight unlabeled data in semi-supervised learning.
Adapts self-supervised learning using probabilistic sets with validity guarantees.
In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised learning problem, on which we update the model parameters before making a predi…
We introduce the Neural Conditioner (NC), a self-supervised machine able to learn about all the conditional distributions of a random vector . The NC is a function that leverages adversarial training to match each conditional distribution . After training, the NC generalizes to …
CNNs predict spatial fields from sparse data.
Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech signals, which are often characterized by long sequences with a complex hierarchical structure. Some recent works, however, have shown that it is possible to derive useful speech repr…
To explore underlying complementary information from multiple views, in this paper, we propose a novel Latent Multi-view Semi-Supervised Classification (LMSSC) method. Unlike most existing multi-view semi-supervised classification methods that learn the graph using original features, our method seeks an underlying late…
NLP tasks are often limited by scarcity of manually annotated data. In social media sentiment analysis and related tasks, researchers have therefore used binarized emoticons and specific hashtags as forms of distant supervision. Our paper shows that by extending the distant supervision to a more diverse set of noisy la…
FROST speeds up and stabilizes one-shot semi-supervised learning.
In this work, we generalize semi-supervised generative adversarial networks (GANs) from classification problems to regression problems. In the last few years, the importance of improving the training of neural networks using semi-supervised training has been demonstrated for classification problems. We present a novel …
In this work, we introduce a novel framework that employs cluster annotation to boost active learning by reducing the number of human interactions required to train deep neural networks. Instead of annotating single samples individually, humans can also label clusters, producing a higher number of annotated samples wit…
The paper investigates how supervised learning and self-play improve sample efficiency in teaching AI to communicate.
A significant challenge to make learning techniques more suitable for general purpose use is to move beyond i) complete supervision, ii) low dimensional data, iii) a single task and single view per instance. Solving these challenges allows working with "Big Data" problems that are typically high dimensional with multip…
Weakly-supervised RL identifies meaningful tasks, improving performance in complex environments.
Self-supervised ECG learning improves emotion recognition.
The paper proposes machine learning models for option pricing without using historical or implied volatility.
MarkerMap selects key genes for cell type analysis in single-cell RNA-seq.
New method disentangles hidden data structures using HSIC and supervision.
Paper tackles RUL prediction with scarce data using indirect supervision.
Deep learning identifies transcriptomic patterns and cell types associated with SARS-CoV-2 infection and COVID-19 severity.
Supervised topic models simultaneously model the latent topic structure of large collections of documents and a response variable associated with each document. Existing inference methods are based on variational approximation or Monte Carlo sampling, which often suffers from the local minimum defect. Spectral methods …
The paper introduces a method to measure the benefits of incidental supervision signals.
A new method improves semi-supervised learning by handling tasks with different attribute spaces.
One-hot CNN (convolutional neural network) has been shown to be effective for text categorization (Johnson & Zhang, 2015). We view it as a special case of a general framework which jointly trains a linear model with a non-linear feature generator consisting of `text region embedding + pooling'. Under this framework, we…
New method extracts brain age from MRI sequences over time.
Study learning from multiple thinkers providing step-by-step solutions to problems.
New analysis reveals masked self-supervised learning's effectiveness in extracting data structure.
DBT combines diffusion models and boosting for supervised learning.
Generative Adapter adapts LMs with a single forward pass, reducing inference overhead.
Training convolutional networks (CNN's) that fit on a single GPU with minibatch stochastic gradient descent has become effective in practice. However, there is still no effective method for training large CNN's that do not fit in the memory of a few GPU cards, or for parallelizing CNN training. In this work we show tha…