arXiv research

FedAMD framework improves federated learning with partial client participation.

Artemis framework improves distributed learning with bidirectional compression and partial participation.

FedAvg converges linearly to global minimum in federated learning with partial participation.

FedSGM tackles constrained federated learning with unified framework.

New framework provides privacy guarantees for practical federated learning.

This paper analyzes error feedback in compressed federated learning for non-convex optimization problems.

Unified analysis of FL with arbitrary client participation.

A new method for efficient online federated learning reduces communication overhead.

Paper proposes SCALLION and SCAFCOM for compressed FL with reduced communication.

We consider a financial market model with a single risky asset whose price process evolves according to a general jump-diffusion with locally bounded coefficients and where market participants have only access to a partial information flow. For any utility function, we prove that the partial information financial marke…

Unified analysis of Federated Averaging and Nesterov FedAvg for linear speedup.

FedAVOT improves federated learning by aligning user distributions.

Federated learning enables a large amount of edge computing devices to jointly learn a model without data sharing. As a leading algorithm in this setting, Federated Averaging (\texttt{FedAvg}) runs Stochastic Gradient Descent (SGD) in parallel on a small subset of the total devices and averages the sequences only once …

Proposes SROF for row-wise fusion in federated learning for multivariate responses.

New algorithm reduces communication time in federated learning.

We propose a new optimization formulation for training federated learning models. The standard formulation has the form of an empirical risk minimization problem constructed to find a single global model trained from the private data stored across all participating devices. In contrast, our formulation seeks an explici…

Optimizes capital structure for life insurance companies with surplus participation.

The paper uncovers two key laws of market impact influenced by volume and participation rate.

Federated learning (FL) is a heavily promoted approach for training ML models on sensitive data, e.g., text typed by users on their smartphones. FL is expressly designed for training on data that are unbalanced and non-iid across the participants. To ensure privacy and integrity of the fedeated model, latest FL approac…

Federated learning (FL) is a privacy-preserving paradigm for training collective machine learning models with locally stored data from multiple participants. Vertical federated learning (VFL) deals with the case where participants sharing the same sample ID space but having different feature spaces, while label informa…

Oft-cited causes of mini-flash crashes include human errors, endogenous feedback loops, the nature of modern liquidity provision, fundamental value shocks, and market fragmentation. We develop a mathematical model which captures aspects of the first three explanations. Empirical features of recent mini-flash crashes ar…

Paper tackles unknown participation in FL, proposing FedAU for better performance.

This paper analyzes and improves convergence in federated learning with biased client selection.

The purpose of this article is to introduce, analyze and compare two performance participation methods based on a portfolio consisting of two risky assets: Option-Based Performance Participation (OBPP) and Constant Proportion Performance Participation (CPPP). By generalizing the provided guarantee to a participation in…

SA-PEF improves federated learning efficiency by correcting gradient mismatches.

Extended model ensures long-term survival of traders in limited stock market participation.

New data improves market impact estimation methods.

Data poisoning attacks can severely degrade FL models, especially targeting specific classes.

In this paper, we present a new task that investigates how people interact with and make judgments about towers of blocks. In Experiment~1, participants in the lab solved a series of problems in which they had to re-configure three blocks from an initial to a final configuration. We recorded whether they used one hand …

New method detects careless responding in long surveys.

Proves existence of equilibrium in limited participation economy.

In the Pioneer 100 (P100) Wellness Project (Price and others, 2017), multiple types of data are collected on a single set of healthy participants at multiple timepoints in order to characterize and optimize wellness. One way to do this is to identify clusters, or subgroups, among the participants, and then to tailor pe…

Entropy regularization improves sparse model discovery in federated learning.

Flexible device participation improves federated learning convergence.

Neuroimaging studies produce gigabytes of spatio-temporal data for a small number of participants and stimuli. Rarely do researchers attempt to model and examine how individual participants vary from each other -- a question that should be addressable even in small samples given the right statistical tools. We propose …

Federated learning leaks participant dataset quality even with secure aggregation.

Federated learning is a distributed framework according to which a model is trained over a set of devices, while keeping data localized. This framework faces several systems-oriented challenges which include (i) communication bottleneck since a large number of devices upload their local updates to a parameter server, a…

New algorithm achieves linear speedup in non-i.i.d. federated bilevel learning.

We consider trading against a hedge fund or large trader that must liquidate a large position in a risky asset if the market price of the asset crosses a certain threshold. Liquidation occurs in a disorderly manner and negatively impacts the market price of the asset. We consider the perspective of small investors whos…

Mandatory emission trading schemes are being established around the world. Participants of such market schemes are always exposed to risks. This leads to the creation of an accompanying market for emission-linked derivatives. To evaluate the fair prices of such financial products, one needs appropriate models for the e…

A new federated learning framework ensures fairness and robustness.

Federated learning enables the creation of a powerful centralized model without compromising data privacy of multiple participants. While successful, it does not incorporate the case where each participant independently designs its own model. Due to intellectual property concerns and heterogeneous nature of tasks and d…

P3LS preserves privacy while integrating data across companies.

ADRL improves participant selection in MCS systems.

Federated learning enables training collaborative machine learning models at scale with many participants whilst preserving the privacy of their datasets. Standard federated learning techniques are vulnerable to Byzantine failures, biased local datasets, and poisoning attacks. In this paper we introduce Adaptive Federa…

Automatic differentiation is involved for long in applied mathematics as an alternative to finite difference to improve the accuracy of numerical computation of derivatives. Each time a numerical minimization is involved, automatic differentiation can be used. In between formal derivation and standard numerical schemes…

Study uses ML to predict non-participation in ELSA COVID-19 follow-up studies.

This paper addresses privacy in federated learning with wireless clients and base stations.