Research
On-device research index

arXiv research

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.

168,694 papers · 148 categories

Trend · papers per month

491317 · Mar 202019922001200920172026
48 results for Client Stratification

FedSTaS stratifies and samples clients for efficient FL.

problem Inefficient client sampling in federated learning.
method Stratifies clients based on compressed gradients, uses Neyman allocation for sampling, and samples local data uniformly.
result FedSTaS achieves higher accuracy than FedSTS in fixed training rounds.

We prove the existence of Verdier stratifications for sets definable in any o-minimal structure on (R, +, .). It is also shown that the Verdier condition (w) implies the Whitney condition (b) in o-minimal structures on (R, +, .). As a consequence the Whitney Stratification Theorem holds. The existence of (wf)-stratific…

1997-04-14abs ↗pdf ↗

The paper studies HKKN stratifications for non-compact spaces and proves convexity properties.

problem Proving convexity properties of moment maps for non-compact subsets.
method Algebraic and analytical study of HKKN stratifications for a vector space and compact Kähler manifold, then applying to non-compact subsets.
result Convexity properties of moment maps for invariant subsets are proven.

Stratifies representation varieties of twisted Hopf links.

problem Stratifying representation varieties of twisted Hopf links.
method Using stratification of AGLr(C)\mathrm{AGL}_r(\mathbb{C})-representation varieties of the fundamental group of the complement of a twisted Hopf link.
result Explicit description and computation of motives for ranks 1 and 2.

The paper defines a stratification for Lie groupoids in a tame topology context.

problem Presenting a tame topology counterpart to canonical stratification of Lie groupoids.
method Using Shiota's isotopy lemma and approximation theorem, the paper defines a canonical Whitney stratification of definable Lie groupoids into invariant strata.
result A canonical Whitney stratification of the Lie groupoid into definable strata invariant under the groupoid action.

Client adaptation improves federated learning performance with non-IID data.

problem Improving model performance in federated learning with non-identically and non-independently distributed data.
method Simulates heterogeneous clients to learn client-specific conditioning using a conditional gated activation unit.
result Client adaptation enhances model performance across balanced and imbalanced data sets from audio and image domains.

New stratification reveals intrinsic singularity types of orbit spaces.

problem Understanding the intrinsic structure of orbit spaces under Lie group actions.
method Introduced the isostabilizer decomposition and established a map to Klein strata.
result A new canonical stratification on the manifold clarifies the relationship with classical structures.

Social media enhances or diminishes scientific status, depending on usage.

problem Impact of social media on scientific stratification and mobility.
method Logistic Attribution Analysis combining statistical and machine learning methods.
result Social media promotes stratification and mobility, but beyond a threshold, it negatively impacts status.

Study clarifies variance of stratification estimators for causal effects.

problem Estimating average causal effects with discrete covariates.
method Combines insights from potential outcomes, causal diagrams, and structural models.
result Derives expressions for the variance of stratification estimators.

This paper provides a stratification of semi-algebraic sets in the plane with finitely many geodesic segments.

problem How to stratify semi-algebraic sets in the plane with finitely many geodesic segments.
method Develops a semi-algebraic stratification of a real semi-algebraic set in the plane with open cells having the finiteness property.
result Provides insights for high-dimensional stratifications of semi-algebraic sets in connection with geodesics.

We study the topology of the inertia space of a smooth GG-manifold MM where GG is a compact Lie group. We construct an explicit Whitney stratification of the inertia space, demonstrating that the inertia space is a triangulable differentiable stratified space. In addition, we demonstrate a de Rham theorem for differ…

2012-07-03abs ↗pdf ↗

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

problem Analyzing convergence in federated learning with biased client selection.
method First convergence analysis of federated optimization for biased client selection strategies, proposing Power-of-Choice framework.
result Power-of-Choice strategies converge up to 3 times faster and give 10% higher test accuracy than random selection.

This paper optimizes brokerage contracts for multiple clients trading a single asset.

problem Optimizing brokerage contracts for multiple clients trading a single asset.
method Endogenously determines clients' reservation values and strategically chooses clients. Characterizes optimal portfolios computationally.
result Characterizes optimal portfolios of clients and their profits, showing dependence on price impact coefficients.

Personalized federated learning for diverse client objectives.

problem Training a single global model across diverse local datasets is not optimal.
method Efficiently calculates optimal weighted model combinations for each client based on their specific objectives.
result Our method outperforms existing alternatives and enables new personalized features.

The paper describes a stratification of a compactified Hurwitz space using combinatorial trees.

problem Describing the boundary stratification of a compactified Hurwitz space.
method Using decorated trees to describe the boundary strata and their containment relations.
result The boundary strata of the compactified Hurwitz space are in bijection with decorated trees, and containment is given by edge contraction.

Federated learning is a recent advance in privacy protection. In this context, a trusted curator aggregates parameters optimized in decentralized fashion by multiple clients. The resulting model is then distributed back to all clients, ultimately converging to a joint representative model without explicitly having to s…

2017-12-20abs ↗pdf ↗

Let GG be a Lie group, and let (M,ω)(M,ω) be a symplectic manifold. If GG admits a Hamiltonian action on (M,ω)(M,ω) with momentum map μμ, then MM, the zero-level set of μμ, the orbit space, and the corresponding symplectic quotient all have induced stratifications. We push this setting into the language of differential …

2011-04-20abs ↗pdf ↗

FedAMD framework improves federated learning with partial client participation.

problem Data heterogeneity and inactive client updates in partial client participation.
method Anchor sampling divides clients into anchor and miner groups, using large and small batches respectively.
result FedAMD achieves faster convergence and improved model performance compared to state-of-the-art methods.

Federated Learning allows for population level models to be trained without centralizing client data by transmitting the global model to clients, calculating gradients locally, then averaging the gradients. Downloading models and uploading gradients uses the client's bandwidth, so minimizing these transmission costs is…

2019-09-27abs ↗pdf ↗

Federated framework learns causal states to predict counterfactuals without centralizing data.

problem Decentralized counterfactual reasoning in coupled industrial systems with private data.
method Federated causal representation learning in state-space systems.
result Proves convergence to centralized oracle and provides privacy guarantees.

Unified Bayesian framework for clustered federated learning improves model performance.

problem Handling non-IID client data in federated learning.
method A unified Bayesian framework for clustered federated learning that associates clients to clusters and proposes practical algorithms for data associations.
result The proposed framework increases model performance by circumventing the need for unique client-cluster associations.

The paper offers simple, near-optimal algorithms for multi-group learning.

problem Learning predictors within subgroups of a population, addressing fairness and hidden stratification.
method Studies the structure of solutions and provides simple, near-optimal algorithms.
result Simple and near-optimal algorithms for multi-group learning.

The monster tower is a tower of spaces over a specified base; each space in the tower is a parameter space for curvilinear data up to a specified order. We describe and analyze a natural stratification of these spaces.

2016-06-25abs ↗pdf ↗

FLowDUP trains personalized models with unlabeled clients in low dimensions.

problem Training personalized models on clients with only unlabeled data.
method FLowDUP uses a forward pass with unlabeled data and a transductive PAC-Bayesian bound to generate personalized models in a low-dimensional subspace.
result FLowDUP enables efficient communication and computation with personalized models generated from unlabeled data.

We introduce a natural stratification of the space of projective classes of measured laminations on a complete hyperbolic surface of finite area. We prove a rigidity result, namely, the group of self-homeomorphisms of the space of projective measured laminations that preserve such a stratification is in general identif…

2019-10-30abs ↗pdf ↗

DFedAvgM is a decentralized FedAvg with momentum for privacy and communication efficiency.

problem Efficiently train models with privacy and communication efficiency in federated learning.
method Decentralized Federated Averaging with Momentum (DFedAvgM) on clients connected by an undirected graph, using stochastic gradient descent with momentum and quantization.
result DFedAvgM converges under trivial assumptions and can be improved with the PŁ property, numerically verified.

Study chaotic dynamics in social stratification models leading to thermalization and turbulence.

problem Understanding social stratification dynamics through chaotic nonlinear systems.
method Modeling social network links with oscillators and energies, studying Hamiltonian evolution and nonlinear interactions.
result Chaotic dynamics leads to dynamical thermalization and Kolmogorov-Zakharov turbulence, with implications for wealth inequality.

In federated learning systems, clients are autonomous in that their behaviors are not fully governed by the server. Consequently, a client may intentionally or unintentionally deviate from the prescribed course of federated model training, resulting in abnormal behaviors, such as turning into a malicious attacker or a …

2019-10-22abs ↗pdf ↗

Group personalization improves FL performance in heterogeneous client data.

problem Mitigating client drift in federated learning with heterogeneous data.
method Fine-tuning a global FL model over homogeneous groups of clients, then personalizing each group's model.
result The proposed method achieves superior personalization performance compared to other FL approaches.

FedACS uses attention to select clients with similar data for federated learning.

problem Non-IID data and data scarcity in federated learning.
method FedACS integrates an attention mechanism to prioritize clients with similar data distributions.
result FedACS improves federated learning performance by addressing non-IID data and data scarcity.

Study almost rigidity of super Ricci flow with non-negative Muller quantity.

problem Almost rigidity properties of super Ricci flow with non-negative Muller quantity.
method Almost splitting and quantitative stratification theorems established by Bamler for Ricci flow.
result Obtained almost constancy for a certain integral quantity concerning scalar curvature at an almost self-similar point.

Study identifies and estimates treatment effect heterogeneity within principal stratification subpopulations.

problem Causal inference with intermediate outcomes and treatment effect heterogeneity.
method Proposes a novel doubly cross-fit doubly robust machine learner to efficiently learn conditional principal causal effects under principal ignorability.
result Demonstrates informative patterns of treatment effect heterogeneity within the always-survivor subpopulation in an acute lung injury trial.