75 citations · 897 across the 91 of their papers we have counts for
12 papers · 1 filter
How Do You Want Your Greedy: Simultaneous or Repeated?
Moran Feldman, Christopher Harshaw, Amin Karbasi
We present SimultaneousGreedys, a deterministic algorithm for constrained submodular maximization. At a high level, the algorithm maintains solutions and greedily updates th…
Multiple Descent: Design Your Own Generalization Curve
Lin Chen, Yifei Min, Mikhail Belkin +1
This paper explores the generalization loss of linear regression in variably parameterized families of models, both under-parameterized and over-parameterized. We show that the gen…
Meta Learning in the Continuous Time Limit
Ruitu Xu, Lin Chen, Amin Karbasi
In this paper, we establish the ordinary differential equation (ODE) that underlies the training dynamics of Model-Agnostic Meta-Learning (MAML). Our continuous-time limit view of…
Safe Learning under Uncertain Objectives and Constraints
Mohammad Fereydounian, Zebang Shen, Aryan Mokhtari +2
In this paper, we consider non-convex optimization problems under \textit{unknown} yet safety-critical constraints. Such problems naturally arise in a variety of domains including…
Continuous Submodular Maximization: Beyond DR-Submodularity
Moran Feldman, Amin Karbasi
In this paper, we propose the first continuous optimization algorithms that achieve a constant factor approximation guarantee for the problem of monotone continuous submodular maxi…
Submodularity in Action: From Machine Learning to Signal Processing Applications
Ehsan Tohidi, Rouhollah Amiri, Mario Coutino +3
Submodularity is a discrete domain functional property that can be interpreted as mimicking the role of the well-known convexity/concavity properties in the continuous domain. Subm…