30 citations · 60 across the 13 of their papers we have counts for
10 papers · 1 filter
Flexible Routing via Uncertainty Decomposition
Charlotte Peale, Siddartha Devic, Parikshit Gopalan +2
A key strategy for balancing performance and cost in modern machine learning systems is to dynamically route queries to either a low-cost model or a more expensive oracle (such as…
When unlearning is free: leveraging low influence points to reduce computational costs
Anat Kleiman, Robert Fisher, Ben Deaner +1
As concerns around data privacy in machine learning grow, the ability to unlearn, or remove, specific data points from trained models becomes increasingly important. While state of…
When does a predictor know its own loss?
Aravind Gollakota, Parikshit Gopalan, Aayush Karan +2
Given a predictor and a loss function, how well can we predict the loss that the predictor will incur on an input? This is the problem of loss prediction, a key computational task…
Provable Uncertainty Decomposition via Higher-Order Calibration
Gustaf Ahdritz, Aravind Gollakota, Parikshit Gopalan +2
We give a principled method for decomposing the predictive uncertainty of a model into aleatoric and epistemic components with explicit semantics relating them to the real-world da…
Loss Minimization through the Lens of Outcome Indistinguishability
Parikshit Gopalan, Lunjia Hu, Michael P. Kim +2
We present a new perspective on loss minimization and the recent notion of Omniprediction through the lens of Outcome Indistingusihability. For a collection of losses and hypothesi…
KL Divergence Estimation with Multi-group Attribution
Parikshit Gopalan, Nina Narodytska, Omer Reingold +2
Estimating the Kullback-Leibler (KL) divergence between two distributions given samples from them is well-studied in machine learning and information theory. Motivated by considera…