Search Results for author:
Found 11 papers, 1 papers with code
Iterative Sketching for Secure Coded Regression
Linear regression is a fundamental and primitive problem in supervised machine learning, with applications ranging from epidemiology to finance.
Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes
Next, we derive the soft-decision based version of our algorithm, called soft-subRPA, that not only improves upon the performance of subRPA but also enables a differentiable decoding algorithm.
Federated Learning with Heterogeneous Differential Privacy
We propose a new algorithm for FL with heterogeneous DP, named FedHDP, which employs personalization and weighted averaging at the server using the privacy choices of clients, to achieve better performance on clients' local models.
ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems
While this learning-based approach is more resource-efficient than replication, it is tailored to the specific model hosted by the cloud and is particularly suitable for a small number of queries (typically less than four) and tolerating very few (mostly one) number of stragglers.
KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learning
In this paper, we construct KO codes, a computationaly efficient family of deep-learning driven (encoder, decoder) pairs that outperform the state-of-the-art reliability performance on the standardized AWGN channel.
Reed-Muller Subcodes: Machine Learning-Aided Design of Efficient Soft Recursive Decoding
To lower the complexity of our decoding algorithm, referred to as subRPA in this paper, we investigate different ways for pruning the projections.
Information Theory Information Theory
List-Decodable Coded Computing: Breaking the Adversarial Toleration Barrier
We further propose folded Lagrange coded computing (FLCC) to incorporate the developed techniques into a specific coded computing setting.
Coded Machine Unlearning
We also present the corresponding unlearning protocol and show that it satisfies the perfect unlearning criterion.
Analog Lagrange Coded Computing
Also, the accuracy of outcome is characterized in a practical setting assuming operations are performed using floating-point numbers.
Privacy-Preserving Distributed Learning in the Analog Domain
Then numerical results are shown for experiments on the MNIST dataset.
Coding for Crowdsourced Classification with XOR Queries
In this paper we leverage the connections between this problem and well-studied codes with sparse representations for the channel coding problem to provide querying schemes with almost optimal number of queries, each of which involving only a constant number of labels.
