Recently, DARPA launched the ShELL program, which aims to explore how
ex...
We study how to release summary statistics on a data stream subject to t...
In federated frequency estimation (FFE), multiple clients work together ...
While Deep Reinforcement Learning has been widely researched in medical
...
Deep reinforcement learning(DRL) is increasingly being explored in medic...
A coreset is a tiny weighted subset of an input set, that closely resemb...
Recent research has observed that in machine learning optimization, grad...
Many streaming algorithms provide only a high-probability relative
appro...
We consider a continual learning (CL) problem with two linear regression...
Federated learning is a recent development in the machine learning area ...
Radial basis function neural networks (RBFNN) are well-known for
their c...
This paper considers the problem of learning a single ReLU neuron with
s...
Selective experience replay is a popular strategy for integrating lifelo...
Graph Neural Networks (GNNs) are powerful deep learning methods for
Non-...
Motivated by practical generalizations of the classic k-median and
k-mea...
We study linear regression under covariate shift, where the marginal
dis...
Since the advent of Federated Learning (FL), research has applied these
...
We study streaming algorithms in the white-box adversarial model, where ...
Continual/lifelong learning from a non-stationary input data stream is a...
(j,k)-projective clustering is the natural generalization of the family ...
Stochastic gradient descent (SGD) has achieved great success due to its
...
Federated learning is increasingly being explored in the field of medica...
Stochastic gradient descent (SGD) has been demonstrated to generalize we...
The sliding window model generalizes the standard streaming model and of...
For the problem of task-agnostic reinforcement learning (RL), an agent f...
Stochastic gradient descent (SGD) exhibits strong algorithmic regulariza...
We provide the first coreset for clustering points in ℝ^d that
have mult...
In this paper, we introduce adversarially robust streaming algorithms fo...
Preventing catastrophic forgetting while continually learning new tasks ...
We analyze the popular kernel polynomial method (KPM) for approximating ...
There is an increasing realization that algorithmic inductive biases are...
In this paper we consider multi-objective reinforcement learning where t...
Running machine learning analytics over geographically distributed datas...
Understanding the algorithmic regularization effect of stochastic gradie...
Many real-world data sets are sparse or almost sparse. One method to mea...
Model compression is crucial for deployment of neural networks on device...
Regularization for optimization is a crucial technique to avoid overfitt...
Existing approaches to federated learning suffer from a communication
bo...
Coresets are modern data-reduction tools that are widely used in data
an...
In streaming Singular Value Decomposition (SVD), d-dimensional rows of a...
Network performance problems are notoriously difficult to diagnose. Prio...
A current clinical challenge is identifying limb girdle muscular dystrop...
In the time-decay model for data streams, elements of an underlying data...
The spectrum of a matrix contains important structural information about...
We initiate the study of coresets for clustering in graph metrics, i.e.,...
Model compression provides a means to efficiently deploy deep neural net...
Approximating quantiles and distributions over streaming data has been
s...
Large-scale distributed training of neural networks is often limited by
...
We design coresets for Ordered k-Median, a generalization of classical
c...
We resolve the randomized one-way communication complexity of Dynamic Ti...