3 citations · 7 across the 13 of their papers we have counts for
13 papers
Deep Model Merging: The Sister of Neural Network Interpretability -- A Survey
Arham Khan, Todd Nief, Nathaniel Hudson +6
We survey the model merging literature through the lens of loss landscape geometry to connect observations from empirical studies on model merging and loss landscape analysis to ph…
Mitigating Memorization In Language Models
Mansi Sakarvadia, Aswathy Ajith, Arham Khan +6
Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that d…
Flight: A FaaS-Based Framework for Complex and Hierarchical Federated Learning
Nathaniel Hudson, Valerie Hayot-Sasson, Yadu Babuji +5
Federated Learning (FL) is a decentralized machine learning paradigm where models are trained on distributed devices and are aggregated at a central server. Existing FL frameworks…
TaPS: A Performance Evaluation Suite for Task-based Execution Frameworks
J. Gregory Pauloski, Valerie Hayot-Sasson, Maxime Gonthier +5
Task-based execution frameworks, such as parallel programming libraries, computational workflow systems, and function-as-a-service platforms, enable the composition of distinct tas…
Causal Discovery over High-Dimensional Structured Hypothesis Spaces with Causal Graph Partitioning
Ashka Shah, Adela DePavia, Nathaniel Hudson +2
The aim in many sciences is to understand the mechanisms that underlie the observed distribution of variables, starting from a set of initial hypotheses. Causal discovery allows us…
Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision
Nathaniel Hudson, J. Gregory Pauloski, Matt Baughman +13
Deep learning methods are transforming research, enabling new techniques, and ultimately leading to new discoveries. As the demand for more capable AI models continues to grow, we…
Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism
Mansi Sakarvadia, Arham Khan, Aswathy Ajith +5
Transformer-based Large Language Models (LLMs) are the state-of-the-art for natural language tasks. Recent work has attempted to decode, by reverse engineering the role of linear l…
Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models
Mansi Sakarvadia, Aswathy Ajith, Arham Khan +5
Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Large Language Models (LLMs) struggle to perform such reasoning consi…
Adversarial Predictions of Data Distributions Across Federated Internet-of-Things Devices
Samir Rajani, Dario Dematties, Nathaniel Hudson +4
Federated learning (FL) is increasingly becoming the default approach for training machine learning models across decentralized Internet-of-Things (IoT) devices. A key advantage of…
Accelerating Communications in Federated Applications with Transparent Object Proxies
J. Gregory Pauloski, Valerie Hayot-Sasson, Logan Ward +5
Advances in networks, accelerators, and cloud services encourage programmers to reconsider where to compute -- such as when fast networks make it cost-effective to compute on remot…
Hierarchical and Decentralised Federated Learning
Omer Rana, Theodoros Spyridopoulos, Nathaniel Hudson +4
Federated learning has shown enormous promise as a way of training ML models in distributed environments while reducing communication costs and protecting data privacy. However, th…
QoS-Aware Placement of Deep Learning Services on the Edge with Multiple Service Implementations
Nathaniel Hudson, Hana Khamfroush, Daniel E. Lucani
Mobile edge computing pushes computationally-intensive services closer to the user to provide reduced delay due to physical proximity. This has led many to consider deploying deep…
Smart Advertisement for Maximal Clicks in Online Social Networks Without User Data
Nathaniel Hudson, Hana Khamfroush, Brent Harrison +1
Click-through rate (CTR) prediction of advertisements on online social network platforms to optimize advertising is of much interest. Prior works build machine learning models that…