Renaud Gaucher
@renaudgaucher.bsky.social
PhD student at École polytechnique. Optimization, machine learning, robustness
renaudgaucher.github.io
renaudgaucher.github.io
This work opens the way to more secure distributed systems, for collaborative machine learning, and beyond!
June 12, 2025 at 6:06 PM
This work opens the way to more secure distributed systems, for collaborative machine learning, and beyond!
We show that it can be combined with many robust averaging options and the resulting algorithm is highly resilient: the performance remains strong when the number of misbehaving computers doesn’t exceed a threshold. For an averaging technique we introduce, this threshold is optimal up to a factor 2!
June 12, 2025 at 6:06 PM
We show that it can be combined with many robust averaging options and the resulting algorithm is highly resilient: the performance remains strong when the number of misbehaving computers doesn’t exceed a threshold. For an averaging technique we introduce, this threshold is optimal up to a factor 2!
We investigate this challenge in a setting where computers communicate in peer-to-peer, without relying on a central server.
Our approach builds on a simple idea: each computer can treat its information as a trustworthy reference and consider messages that differ too much as suspicious.
Our approach builds on a simple idea: each computer can treat its information as a trustworthy reference and consider messages that differ too much as suspicious.
June 12, 2025 at 6:05 PM
We investigate this challenge in a setting where computers communicate in peer-to-peer, without relying on a central server.
Our approach builds on a simple idea: each computer can treat its information as a trustworthy reference and consider messages that differ too much as suspicious.
Our approach builds on a simple idea: each computer can treat its information as a trustworthy reference and consider messages that differ too much as suspicious.