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.
Minimal variations guide unsupervised learning for better downstream tasks.
Large amounts of labeled data are typically required to train deep learning models. For many real-world problems, however, acquiring additional data can be expensive or even impossible. We present semi-supervised deep kernel learning (SSDKL), a semi-supervised regression model based on minimizing predictive variance in…
We consider the task of training classifiers without labels. We propose a weakly supervised method---adversarial label learning---that trains classifiers to perform well against an adversary that chooses labels for training data. The weak supervision constrains what labels the adversary can choose. The method therefore…
Novel semi-supervised method for X-ray classification with minimal labels.
Deep learning for HJB PDEs using synthetic data and residual minimization.
FSBM improves matching efficiency with minimal supervision.
Paper explores VRM for PSMLC with partially labeled medical images.
Semi-supervised learning improves prediction using unlabeled data.
New attacks prevent both supervised and contrastive learning from private data.
New algorithm for safer machine learning with different testing and training distributions.
We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training. Our work builds on the Ladder network proposed by Valpola (…
Unified framework for N-tuples learning improves weakly supervised tasks.
Radio emitter recognition in dense multi-user environments is an important tool for optimizing spectrum utilization, identifying and minimizing interference, and enforcing spectrum policy. Radio data is readily available and easy to obtain from an antenna, but labeled and curated data is often scarce making supervised …
We show how a deep denoising autoencoder with lateral connections can be used as an auxiliary unsupervised learning task to support supervised learning. The proposed model is trained to minimize simultaneously the sum of supervised and unsupervised cost functions by back-propagation, avoiding the need for layer-wise pr…
Empirical risk minimization (ERM), with proper loss function and regularization, is the common practice of supervised classification. In this paper, we study training arbitrary (from linear to deep) binary classifier from only unlabeled (U) data by ERM. We prove that it is impossible to estimate the risk of an arbitrar…
Zero loss is achievable in overparametrized DL networks under specific conditions.
Unified VAE framework improves unsupervised, semi-supervised, and supervised learning.
We present an objective function for learning with unlabeled data that utilizes auxiliary expectation constraints. We optimize this objective function using a procedure that alternates between information and moment projections. Our method provides an alternate interpretation of the posterior regularization framework (…
This paper analyzes the landscape of supervised contrastive loss in over-parameterized networks.
Different types of training data have led to numerous schemes for supervised classification. Current learning techniques are tailored to one specific scheme and cannot handle general ensembles of training data. This paper presents a unifying framework for supervised classification with general ensembles of training dat…
We introduce a new convex optimization problem, termed quadratic decomposable submodular function minimization. The problem is closely related to decomposable submodular function minimization and arises in many learning on graphs and hypergraphs settings, such as graph-based semi-supervised learning and PageRank. We ap…
This work shows that supervised contrastive learning achieves similar results to cross-entropy but requires more iterations.
We show how to train a quantum network of pairwise interacting qubits such that its evolution implements a target quantum algorithm into a given network subset. Our strategy is inspired by supervised learning and is designed to help the physical construction of a quantum computer which operates with minimal external cl…
Paper tackles active labeling for partial supervision.
NS3L improves SSL algorithms by adding negative sampling, achieving better results.
New approach for semi-supervised learning under covariate shifts.
SuNCEt accelerates contrastive learning with minimal labeled data.
Local Clustering improves semi-supervised learning models.
We consider active, semi-supervised learning in an offline transductive setting. We show that a previously proposed error bound for active learning on undirected weighted graphs can be generalized by replacing graph cut with an arbitrary symmetric submodular function. Arbitrary non-symmetric submodular functions can be…
GraphXCOVID uses deep semi-supervised learning to identify COVID-19 from chest X-rays with minimal labels.
Recently, supervised hashing methods have attracted much attention since they can optimize retrieval speed and storage cost while preserving semantic information. Because hashing codes learning is NP-hard, many methods resort to some form of relaxation technique. But the performance of these methods can easily deterior…
Meta-Semi learns to optimize SSL with minimal hyper-parameter tuning.
A new framework for predictive clustering and optimization.
Systems that can automatically analyze EEG signals can aid neurologists by reducing heavy workload and delays. However, such systems need to be first trained using a labeled dataset. While large corpuses of EEG data exist, a fraction of them are labeled. Hand-labeling data increases workload for the very neurologists w…
We introduce a novel semi-supervised version of the least squares classifier. This implicitly constrained least squares (ICLS) classifier minimizes the squared loss on the labeled data among the set of parameters implied by all possible labelings of the unlabeled data. Unlike other discriminative semi-supervised method…
Develops uniform convergence guarantees for a broad class of risk functionals in supervised learning.
ProSMIN improves representation quality through probabilistic self-supervised learning.
Deep semi-supervised learning identifies tree species from natural images.
Supervised topic models can help clinical researchers find interpretable cooccurence patterns in count data that are relevant for diagnostics. However, standard formulations of supervised Latent Dirichlet Allocation have two problems. First, when documents have many more words than labels, the influence of the labels w…
New method extends supervised learning for non-stationary control problems.
This work tackles continual learning with semi-supervised data, showing that even with minimal labeled data, performance can match full-supervised methods.
SGD methods fail to converge to global minimizers in deep neural networks with ReLU activation.
Dimension reduction of multivariate data supervised by auxiliary information is considered. A series of basis for dimension reduction is obtained as minimizers of a novel criterion. The proposed method is akin to continuum regression, and the resulting basis is called continuum directions. With a presence of binary sup…
Method reweights auxiliary tasks to reduce data need for main task.
We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the conditional label distribution around each input data point against local perturbation. Unlike adver…
The paper studies momentum-based minimization for Ginzburg-Landau on Euclidean spaces and graphs.
ERFit identifies dynamic equations from data with minimal supervision.
We present a graph-based variational algorithm for classification of high-dimensional data, generalizing the binary diffuse interface model to the case of multiple classes. Motivated by total variation techniques, the method involves minimizing an energy functional made up of three terms. The first two terms promote a …