28 citations · 127 across the 46 of their papers we have counts for
7 papers · 1 filter
On the Hardness of Learning One Hidden Layer Neural Networks
Shuchen Li, Ilias Zadik, Manolis Zampetakis
In this work, we consider the problem of learning one hidden layer ReLU neural networks with inputs from . We show that this learning problem is hard under standard c…
Smaller Confidence Intervals From IPW Estimators via Data-Dependent Coarsening
Alkis Kalavasis, Anay Mehrotra, Manolis Zampetakis
Inverse propensity-score weighted (IPW) estimators are prevalent in causal inference for estimating average treatment effects in observational studies. Under unconfoundedness, give…
Efficient Statistics With Unknown Truncation, Polynomial Time Algorithms, Beyond Gaussians
Jane H. Lee, Anay Mehrotra, Manolis Zampetakis
We study the estimation of distributional parameters when samples are shown only if they fall in some unknown set . Kontonis, Tzamos, and Zampetakis (FOCS…
Hypercontractivity and factorial moment scaling in the symmetry broken phase
Athanasios Brofas, Manolis Zampetakis, Fotios Diakonos
The search for remnants of the QCD chiral critical point is a central objective of current and future high-energy ion collision experiments. Previous studies suggest that a scaling…
Imperfect-Recall Games: Equilibrium Concepts and Their Complexity
Emanuel Tewolde, Brian Hu Zhang, Caspar Oesterheld +4
We investigate optimal decision making under imperfect recall, that is, when an agent forgets information it once held before. An example is the absentminded driver game, as well a…
Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
Alkis Kalavasis, Amin Karbasi, Argyris Oikonomou +3
As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks.…
Transfer Learning Beyond Bounded Density Ratios
Alkis Kalavasis, Ilias Zadik, Manolis Zampetakis
We study the fundamental problem of transfer learning where a learning algorithm collects data from some source distribution but needs to perform well with respect to a differe…