483 citations · 760 across the 48 of their papers we have counts for
7 papers · 1 filter
From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
Konstantinos Christopher Tsiolis, Alireza Mousavi-Hosseini, Murat A. Erdogdu
To understand feature learning dynamics in neural networks, recent theoretical works have focused on gradient-based learning of Gaussian single-index models, where the label is a n…
Distributional Training Data Attribution: What do Influence Functions Sample?
Bruno Mlodozeniec, Isaac Reid, Sam Power +4
Randomness is an unavoidable part of training deep learning models, yet something that traditional training data attribution algorithms fail to rigorously account for. They ignore…
Beyond Labeling Oracles: What does it mean to steal ML models?
Avital Shafran, Ilia Shumailov, Murat A. Erdogdu +1
Model extraction attacks are designed to steal trained models with only query access, as is often provided through APIs that ML-as-a-Service providers offer. Machine Learning (ML)…
Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning
Tyler Kastner, Murat A. Erdogdu, Amir-massoud Farahmand
We consider the problem of learning models for risk-sensitive reinforcement learning. We theoretically demonstrate that proper value equivalence, a method of learning models which…
-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representations
Adam Dziedzic, Stephan Rabanser, Mohammad Yaghini +3
The lack of well-calibrated confidence estimates makes neural networks inadequate in safety-critical domains such as autonomous driving or healthcare. In these settings, having the…
Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings
Matthew S. Zhang, Murat A. Erdogdu, Animesh Garg
Policy gradient methods have been frequently applied to problems in control and reinforcement learning with great success, yet existing convergence analysis still relies on non-int…
Manipulating SGD with Data Ordering Attacks
Ilia Shumailov, Zakhar Shumaylov, Dmitry Kazhdan +4
Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained…