19 citations · 77 across the 21 of their papers we have counts for
21 papers
(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy
Elan Rosenfeld, Saurabh Garg
We derive an (almost) guaranteed upper bound on the error of deep neural networks under distribution shift using unlabeled test data. Prior methods either give bounds that are vacu…
Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms
Dheeraj Baby, Saurabh Garg, Tzu-Ching Yen +3
This paper focuses on supervised and unsupervised online label shift, where the class marginals varies but the class-conditionals remain invariant. In the unsupervi…
Fog Device-as-a-Service (FDaaS): A Framework for Service Deployment in Public Fog Environments
Sudheer Kumar Battula, Saurabh Garg, James Montgomery +1
Meeting the requirements of future services with time sensitivity and handling sudden load spikes of the services in Fog computing environments are challenging tasks due to the lac…
RLSbench: Domain Adaptation Under Relaxed Label Shift
Saurabh Garg, Nick Erickson, James Sharpnack +3
Despite the emergence of principled methods for domain adaptation under label shift, their sensitivity to shifts in class conditional distributions is precariously under explored.…
CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
Zachary Novack, Julian McAuley, Zachary C. Lipton +1
Open vocabulary models (e.g. CLIP) have shown strong performance on zero-shot classification through their ability generate embeddings for each class based on their (natural langua…
Disentangling the Mechanisms Behind Implicit Regularization in SGD
Zachary Novack, Simran Kaur, Tanya Marwah +2
A number of competing hypotheses have been proposed to explain why small-batch Stochastic Gradient Descent (SGD)leads to improved generalization over the full-batch regime, with re…
Characterizing Datapoints via Second-Split Forgetting
Pratyush Maini, Saurabh Garg, Zachary C. Lipton +1
Researchers investigating example hardness have increasingly focused on the dynamics by which neural networks learn and forget examples throughout training. Popular metrics derived…
Downstream Datasets Make Surprisingly Good Pretraining Corpora
Kundan Krishna, Saurabh Garg, Jeffrey P. Bigham +1
For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the suc…
A Blockchain-based Decentralised and Dynamic Authorisation Scheme for the Internet of Things
Khizar Hameed, Ali Raza, Saurabh Garg +1
An authorisation has been recognised as an important security measure for preventing unauthorised access to critical resources, such as devices and data, within the Internet of Thi…
Unsupervised Learning under Latent Label Shift
Manley Roberts, Pranav Mani, Saurabh Garg +1
What sorts of structure might enable a learner to discover classes from unlabeled data? Traditional approaches rely on feature-space similarity and heroic assumptions on the data.…
Domain Adaptation under Open Set Label Shift
Saurabh Garg, Sivaraman Balakrishnan, Zachary C. Lipton
We introduce the problem of domain adaptation under Open Set Label Shift (OSLS) where the label distribution can change arbitrarily and a new class may arrive during deployment, bu…
Deconstructing Distributions: A Pointwise Framework of Learning
Gal Kaplun, Nikhil Ghosh, Saurabh Garg +2
In machine learning, we traditionally evaluate the performance of a single model, averaged over a collection of test inputs. In this work, we propose a new approach: we measure the…
Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
Saurabh Garg, Sivaraman Balakrishnan, Zachary C. Lipton +2
Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions that may cause performance drops. In this work…
Parallel Multi-Scale Networks with Deep Supervision for Hand Keypoint Detection
Renjie Li, Son Tran, Saurabh Garg +3
Keypoint detection plays an important role in a wide range of applications. However, predicting keypoints of small objects such as human hands is a challenging problem. Recent work…
Mixture Proportion Estimation and PU Learning: A Modern Approach
Saurabh Garg, Yifan Wu, Alex Smola +2
Given only positive examples and unlabeled examples (from both positive and negative classes), we might hope nevertheless to estimate an accurate positive-versus-negative classifie…
SDP: Scalable Real-time Dynamic Graph Partitioner
Md Anwarul Kaium Patwary, Saurabh Garg, Sudheer Kumar Battula +1
Time-evolving large graph has received attention due to their participation in real-world applications such as social networks and PageRank calculation. It is necessary to partitio…
A Taxonomy Study on Securing Blockchain-based Industrial Applications: An Overview, Application Perspectives, Requirements, Attacks, Countermeasures, and Open Issues
Khizar Hameed, Mutaz Barika, Saurabh Garg +2
Blockchain technology has taken on a leading role in today's industrial applications by providing salient features and showing significant performance since its beginning. Blockcha…
RATT: Leveraging Unlabeled Data to Guarantee Generalization
Saurabh Garg, Sivaraman Balakrishnan, J. Zico Kolter +1
To assess generalization, machine learning scientists typically either (i) bound the generalization gap and then (after training) plug in the empirical risk to obtain a bound on th…
A Unified View of Label Shift Estimation
Saurabh Garg, Yifan Wu, Sivaraman Balakrishnan +1
Under label shift, the label distribution p(y) might change but the class-conditional distributions p(x|y) do not. There are two dominant approaches for estimating the label margin…
Code-switched Language Models Using Dual RNNs and Same-Source Pretraining
Saurabh Garg, Tanmay Parekh, Preethi Jyothi
This work focuses on building language models (LMs) for code-switched text. We propose two techniques that significantly improve these LMs: 1) A novel recurrent neural network unit…
Dual Language Models for Code Switched Speech Recognition
Saurabh Garg, Tanmay Parekh, Preethi Jyothi
In this work, we present a simple and elegant approach to language modeling for bilingual code-switched text. Since code-switching is a blend of two or more different languages, a…