Search Results for author:
Found 24 papers, 1 papers with code
FLASH: Federated Learning Across Simultaneous Heterogeneities
The key premise of federated learning (FL) is to train ML models across a diverse set of data-owners (clients), without exchanging local data.
Plug-and-Play Transformer Modules for Test-Time Adaptation
Parameter-efficient tuning (PET) methods such as LoRA, Adapter, and Visual Prompt Tuning (VPT) have found success in enabling adaptation to new domains by tuning small modules within a transformer model.
PPFL: A Personalized Federated Learning Framework for Heterogeneous Population
Personalization aims to characterize individual preferences and is widely applied across many fields.
Causal Rule Learning: Enhancing the Understanding of Heterogeneous Treatment Effect via Weighted Causal Rules
In the rule discovery phase, we utilize a causal forest to generate a pool of causal rules with corresponding subgroup average treatment effects.
FedYolo: Augmenting Federated Learning with Pretrained Transformers
These insights on scale and modularity motivate a new federated learning approach we call "You Only Load Once" (FedYolo): The clients load a full PTF model once and all future updates are accomplished through communication-efficient modules with limited catastrophic-forgetting, where each task is assigned to its own module.
Privacy-Preserving Community Detection for Locally Distributed Multiple Networks
To remove the bias incurred by RR and the squared network matrices, we develop a two-step bias-adjustment procedure.
2D-Shapley: A Framework for Fragmented Data Valuation
Data valuation -- quantifying the contribution of individual data sources to certain predictive behaviors of a model -- is of great importance to enhancing the transparency of machine learning and designing incentive systems for data sharing.
Learning Personalized Brain Functional Connectivity of MDD Patients from Multiple Sites via Federated Bayesian Networks
In particular, we derive a closed-form expression for the local update step and use the iterative proximal projection method to deal with the group fused lasso penalty in the global update step.
Variance reduced Shapley value estimation for trustworthy data valuation
Data valuation, especially quantifying data value in algorithmic prediction and decision-making, is a fundamental problem in data trading scenarios.
Learning Multitask Gaussian Bayesian Networks
We consider the problem of identifying alterations of brain functional connectivity for a single MDD patient.
Toward a Fairness-Aware Scoring System for Algorithmic Decision-Making
Then, we transform the social welfare maximization problem into the risk minimization task in machine learning, and derive a fairness-aware scoring system with the help of mixed integer programming.
Statistical Estimation and Inference via Local SGD in Federated Learning
Both the methods are communication efficient and applicable to online data.
FedPower: Privacy-Preserving Distributed Eigenspace Estimation
The low communication power and the possible privacy breaches of data make the computation of eigenspace challenging.
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
Deep networks are typically trained with many more parameters than the size of the training dataset.
Kernel Interpolation of High Dimensional Scattered Data
Data sites selected from modeling high-dimensional problems often appear scattered in non-paternalistic ways.
Randomized spectral co-clustering for large-scale directed networks
Directed networks are broadly used to represent asymmetric relationships among units.
Uncertainty Quantification for Demand Prediction in Contextual Dynamic Pricing
In this paper, using the problem of demand function prediction in dynamic pricing as the motivating example, we study the problem of constructing accurate confidence intervals for the demand function.
Angle-Based Cost-Sensitive Multicategory Classification
To show the usefulness of the framework, two cost-sensitive multicategory boosting algorithms are derived as concrete instances.
Randomized Spectral Clustering in Large-Scale Stochastic Block Models
In this paper, we study the spectral clustering using randomized sketching algorithms from a statistical perspective, where we typically assume the network data are generated from a stochastic block model that is not necessarily of full rank.
Adaptive Stopping Rule for Kernel-based Gradient Descent Algorithms
In this paper, we propose an adaptive stopping rule for kernel-based gradient descent (KGD) algorithms.
Predicting Depression Severity by Multi-Modal Feature Engineering and Fusion
We present our preliminary work to determine if patient's vocal acoustic, linguistic, and facial patterns could predict clinical ratings of depression severity, namely Patient Health Questionnaire depression scale (PHQ-8).
Learning rates for classification with Gaussian kernels
This paper aims at refined error analysis for binary classification using support vector machine (SVM) with Gaussian kernel and convex loss.
Divide and Conquer Local Average Regression
After theoretically analyzing the pros and cons, we find that although the divide and conquer local average regression can reach the optimal learning rate, the restric- tion to the number of data blocks is a bit strong, which makes it only feasible for small number of data blocks.
Sparse K-Means with $\ell_{\infty}/\ell_0$ Penalty for High-Dimensional Data Clustering
Nevertheless, this framework has two serious drawbacks: One is that the solution of the framework unavoidably involves a considerable portion of redundant noise features in many situations, and the other is that the framework neither offers intuitive explanations on why this framework can select relevant features nor leads to any theoretical guarantee for feature selection consistency.
