Search Results for author:
Found 7 papers, 1 papers with code
Robust Collaborative Learning with Linear Gradient Overhead
We present MoNNA, a new algorithm that (a) is provably robust under standard assumptions and (b) has a gradient computation overhead that is linear in the fraction of faulty machines, which is conjectured to be tight.
Purely Bayesian counterfactuals versus Newcomb's paradox
If these additional data are not expected to reduce sufficiently the predictor's uncertainty on the player's decision, then the player's epistemic system will counterfactually prefer to 2-Box.
Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)
We study Byzantine collaborative learning, where $n$ nodes seek to collectively learn from each others' local data.
Genuinely Distributed Byzantine Machine Learning
The third, Minimum-Diameter Averaging (MDA), is a statistically-robust gradient aggregation rule whose goal is to tolerate Byzantine workers.
A Roadmap for Robust End-to-End Alignment
This paper discussed the {\it robust alignment} problem, that is, the problem of aligning the goals of algorithms with human preferences.
Removing Algorithmic Discrimination (With Minimal Individual Error)
We first solve the problem analytically in the case of two populations, with a uniform bonus-malus on the zones where each population is a majority.
Deep Learning Works in Practice. But Does it Work in Theory?
Deep learning relies on a very specific kind of neural networks: those superposing several neural layers.
