Titouan Parcollet
4 papers in the PaperMetrix corpus
Papers by this author
-
On-device Federated Learning with Flower
2021 · arXiv (Cornell University)
Federated Learning (FL) allows edge devices to collaboratively learn a shared prediction model while keeping their training data on the device, thereby decoupling the ability to do machine learning from the need to store data …
-
ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity
2022 · HAL (Le Centre pour la Communication Scientifique Directe)
International audience
-
An Analysis of Linear Complexity Attention Substitutes with BEST-RQ
2024 · arXiv (Cornell University)
Self-Supervised Learning (SSL) has proven to be effective in various domains, including speech processing. However, SSL is computationally and memory expensive. This is in part due the quadratic complexity of multi-head self-attention (MHSA). Alternatives for …
-
Benchmarking Rotary Position Embeddings for Automatic Speech Recognition
2025 · arXiv (Cornell University)
Self-attention relies on positional embeddings to encode input order. Relative Position (RelPos) embeddings are widely used in Automatic Speech Recognition (ASR). However, RelPos has quadratic time complexity to input length and is often incompatible with …