84 citations · 247 across the 23 of their papers we have counts for
24 papers
DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning
S Ashwin Hebbar, Sravan Kumar Ankireddy, Hyeji Kim +2
Progress in designing channel codes has been driven by human ingenuity and, fittingly, has been sporadic. Polar codes, developed on the foundation of Arikan's polarization kernel,…
Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes
Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva +3
Reed-Muller (RM) codes achieve the capacity of general binary-input memoryless symmetric channels and are conjectured to have a comparable performance to that of random codes in te…
Zonotope Domains for Lagrangian Neural Network Verification
Matt Jordan, Jonathan Hayase, Alexandros G. Dimakis +1
Neural network verification aims to provide provable bounds for the output of a neural network for a given input range. Notable prior works in this domain have either generated bou…
Few-shot Backdoor Attacks via Neural Tangent Kernels
Jonathan Hayase, Sewoong Oh
In a backdoor attack, an attacker injects corrupted examples into the training set. The goal of the attacker is to cause the final trained model to predict the attacker's desired t…
CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family
S Ashwin Hebbar, Viraj Nadkarni, Ashok Vardhan Makkuva +3
Polar codes are widely used state-of-the-art codes for reliable communication that have recently been included in the 5th generation wireless standards (5G). However, there remains…
KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learning
Ashok Vardhan Makkuva, Xiyang Liu, Mohammad Vahid Jamali +3
Landmark codes underpin reliable physical layer communication, e.g., Reed-Muller, BCH, Convolution, Turbo, LDPC and Polar codes: each is a linear code and represents a mathematical…
FedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning
Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti +1
Federated learning (FL) aims to minimize the communication complexity of training a model over heterogeneous data distributed across many clients. A common approach is local method…
Sample Efficient Linear Meta-Learning by Alternating Minimization
Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli +1
Meta-learning synthesizes and leverages the knowledge from a given set of tasks to rapidly learn new tasks using very little data. Meta-learning of linear regression tasks, where t…
SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics
Jonathan Hayase, Weihao Kong, Raghav Somani +1
Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is w…
Efficient Algorithms for Federated Saddle Point Optimization
Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti +1
We consider strongly convex-concave minimax problems in the federated setting, where the communication constraint is the main bottleneck. When clients are arbitrarily heterogeneous…
Reed-Muller Subcodes: Machine Learning-Aided Design of Efficient Soft Recursive Decoding
Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva +3
Reed-Muller (RM) codes are conjectured to achieve the capacity of any binary-input memoryless symmetric (BMS) channel, and are observed to have a comparable performance to that of…
Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise
Xingyu Wang, Sewoong Oh, Chang-Han Rhee
The empirical success of deep learning is often attributed to SGD's mysterious ability to avoid sharp local minima in the loss landscape, as sharp minima are known to lead to poor…
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method
Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli +1
We consider the classical setting of optimizing a nonsmooth Lipschitz continuous convex function over a convex constraint set, when having access to a (stochastic) first-order orac…
Meta-learning for mixed linear regression
Weihao Kong, Raghav Somani, Zhao Song +2
In modern supervised learning, there are a large number of tasks, but many of them are associated with only a small amount of labeled data. These include data from medical image pr…
Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels
Yihan Jiang, Hyeji Kim, Himanshu Asnani +3
Designing codes that combat the noise in a communication medium has remained a significant area of research in information theory as well as wireless communications. Asymptotically…
Proof-of-Stake Longest Chain Protocols: Security vs Predictability
Vivek Bagaria, Amir Dembo, Sreeram Kannan +5
The Nakamoto longest chain protocol is remarkably simple and has been proven to provide security against any adversary with less than 50% of the total hashing power. Proof-of-stake…
Barracuda: The Power of -polling in Proof-of-Stake Blockchains
Giulia Fanti, Jiantao Jiao, Ashok Makkuva +3
A blockchain is a database of sequential events that is maintained by a distributed group of nodes. A key consensus problem in blockchains is that of determining the next block (da…
Privacy-Utility Tradeoffs in Routing Cryptocurrency over Payment Channel Networks
Weizhao Tang, Weina Wang, Giulia Fanti +1
Payment channel networks (PCNs) are viewed as one of the most promising scalability solutions for cryptocurrencies today. Roughly, PCNs are networks where each node represents a us…
Optimal transport mapping via input convex neural networks
Ashok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh +1
In this paper, we present a novel and principled approach to learn the optimal transport between two distributions, from samples. Guided by the optimal transport theory, we learn t…
Robust conditional GANs under missing or uncertain labels
Kiran Koshy Thekumparampil, Sewoong Oh, Ashish Khetan
Matching the performance of conditional Generative Adversarial Networks with little supervision is an important task, especially in venturing into new domains. We design a new trai…
InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
Zinan Lin, Kiran Koshy Thekumparampil, Giulia Fanti +1
Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct…
Learning in Gated Neural Networks
Ashok Vardhan Makkuva, Sewoong Oh, Sreeram Kannan +1
Gating is a key feature in modern neural networks including LSTMs, GRUs and sparsely-gated deep neural networks. The backbone of such gated networks is a mixture-of-experts layer,…
Minimax Rates of Estimating Approximate Differential Privacy
Xiyang Liu, Sewoong Oh
Differential privacy has become a widely accepted notion of privacy, leading to the introduction and deployment of numerous privatization mechanisms. However, ensuring the privacy…
Detecting Sponsored Recommendations
Subhashini Krishnasamy, Rajat Sen, Sewoong Oh +1
With a vast number of items, web-pages, and news to choose from, online services and the customers both benefit tremendously from personalized recommender systems. Such systems how…