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.
One-shot algorithm for feature-distributed kernel PCA reduces communication costs.
FedFisher improves one-shot FL by using Fisher information.
Quantum federated learning improves with non-IID data using one-shot communication.
Bayesian approach reduces FL communication cost by one-shot.
A practical one-shot federated learning algorithm for cross-silo setting.
DOSFL reduces federated learning communication by one round, preserving model performance.
Federated learning supports exact support recovery with minimal communication.
We devise a one-shot approach to distributed sparse regression in the high-dimensional setting. The key idea is to average "debiased" or "desparsified" lasso estimators. We show the approach converges at the same rate as the lasso as long as the dataset is not split across too many machines. We also extend the approach…
We present one-shot federated learning, where a central server learns a global model over a network of federated devices in a single round of communication. Our approach - drawing on ensemble learning and knowledge aggregation - achieves an average relative gain of 51.5% in AUC over local baselines and comes within 90.…
One-shot federated learning method for prediction sets.
Despite the breakthroughs achieved by deep learning models in conventional supervised learning scenarios, their dependence on sufficient labeled training data in each class prevents effective applications of these deep models in situations where labeled training instances for a subset of novel classes are very sparse -…
Study efficient algorithms for one-shot federated conformal prediction.
Synchronous mini-batch SGD is state-of-the-art for large-scale distributed machine learning. However, in practice, its convergence is bottlenecked by slow communication rounds between worker nodes. A natural solution to reduce communication is to use the \emph{`local-SGD'} model in which the workers train their model i…
FONT clusters patients across health systems with privacy and efficiency.
We consider distributed statistical optimization in one-shot setting, where there are machines each observing i.i.d. samples. Based on its observed samples, each machine sends a -bit-long message to a server. The server then collects messages from all machines, and estimates a parameter that minimizes an exp…
We present a novel Newton-type method for distributed optimization, which is particularly well suited for stochastic optimization and learning problems. For quadratic objectives, the method enjoys a linear rate of convergence which provably \emph{improves} with the data size, requiring an essentially constant number of…
CAOS aggregates multiple one-shot predictors for efficient uncertainty quantification.
Efficiently recovers network community structure from clients' small subgraphs.
Study investigates one-shot semi-supervised learning for image classification.
Highly Autonomous Driving (HAD) systems rely on deep neural networks for the visual perception of the driving environment. Such networks are trained on large manually annotated databases. In this work, a semi-parametric approach to one-shot learning is proposed, with the aim of bypassing the manual annotation step requ…
The false discovery rate (FDR)---the expected fraction of spurious discoveries among all the discoveries---provides a popular statistical assessment of the reproducibility of scientific studies in various disciplines. In this work, we introduce a new method for controlling the FDR in meta-analysis of many decentralized…
Paper proposes efficient communication scheme for statistical learning.
New method for one-shot timbre transfer in music.
One-shot neural architecture search (NAS) has played a crucial role in making NAS methods computationally feasible in practice. Nevertheless, there is still a lack of understanding on how these weight-sharing algorithms exactly work due to the many factors controlling the dynamics of the process. In order to allow a sc…
A method to reduce memory usage in NAS by pruning the search space.
Deep learning, even if it is very successful nowadays, traditionally needs very large amounts of labeled data to perform excellent on the classification task. In an attempt to solve this problem, the one-shot learning paradigm, which makes use of just one labeled sample per class and prior knowledge, becomes increasing…
New method simplifies individual claims reserving.
SPECTRE uses spectral conditioning to generate larger graphs without mode collapse.
FROST speeds up and stabilizes one-shot semi-supervised learning.
We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning. Our model learns jointly to represent data and to bind class labels to representations in a single shot. It builds representations via slow weights, learned across tasks through SGD, while fast wei…
This study improves UAV identification using RF signals with one-shot generative methods.
Neural network models that are not conditioned on class identities were shown to facilitate knowledge transfer between classes and to be well-suited for one-shot learning tasks. Following this motivation, we further explore and establish such models and present a novel neural network architecture for the task of weakly…
Less-than-one-shot learning tackles few-shot learning with minimal data.
Convolutional neural networks (CNN) have been shown to provide a good solution for classification problems that utilize data obtained from vibrational spectroscopy. Moreover, CNNs are capable of identification from noisy spectra without the need for additional preprocessing. However, their application in practical spec…
Bonsai-Net efficiently discovers state-of-the-art models with fewer parameters.
Learning from a few examples remains a key challenge in machine learning. Despite recent advances in important domains such as vision and language, the standard supervised deep learning paradigm does not offer a satisfactory solution for learning new concepts rapidly from little data. In this work, we employ ideas from…
DEOT method compares distributions across agents with privacy and efficiency.
Designs efficient algorithms for online and sliding window models of subspace embeddings for all p.
We present a compositional embedding framework that infers not just a single class per input image, but a set of classes, in the setting of one-shot learning. Specifically, we propose and evaluate several novel models consisting of (1) an embedding function f trained jointly with a "composition" function g that compute…
Efficiently optimizes expensive functions with multi-step lookahead using one-shot optimization.
Humans have an impressive ability to reason about new concepts and experiences from just a single example. In particular, humans have an ability for one-shot generalization: an ability to encounter a new concept, understand its structure, and then be able to generate compelling alternative variations of the concept. We…
New approach estimates treatment effects from decentralized data.
Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently. However, few studies have focused on relation types unseen in the original KG, given only one or a few instances for training. To bridge this gap, we propose Co…
New algorithm IAC recovers hidden communities in labeled SBM with optimal performance.
In recent years there has been a sharp rise in networking applications, in which significant events need to be classified but only a few training instances are available. These are known as cases of one-shot learning. Examples include analyzing network traffic under zero-day attacks, and computer vision tasks by sensor…
Neural Architecture Search (NAS) has shown great potentials in finding better neural network designs. Sample-based NAS is the most reliable approach which aims at exploring the search space and evaluating the most promising architectures. However, it is computationally very costly. As a remedy, the one-shot approach ha…
BS-NAS broadens and shrinks search space for optimal neural architectures.
Deep learning for object classification relies heavily on convolutional models. While effective, CNNs are rarely interpretable after the fact. An attention mechanism can be used to highlight the area of the image that the model focuses on thus offering a narrow view into the mechanism of classification. We expand on th…