
Basic Research of AI: Optimization in ML, Federated Learning, GenAI, LLM, Maths for AI, AI for Science Head: DrSc Aleksandr Beznosikov [email protected]
Joined September 2025
- Tweets77
- Following16
- Followers112
- Likes16
BRAInLab retweeted
Training neural networks for tabular regression? Our latest work may be of interest
And it's not only about which of the 18! regression objectives is best, but touches on the role of noise and global early stopping in tabular DL in general
arxiv.org/abs/2610.13909
Thread (1/N)
BRAInLab retweeted
1/10 Muon and Shampoo make optimizer updates matrix-aware. What about weight decay? Our Spectral Weight Decay encourages low-rank weights during training, improving compression and resistance to label noise. We'll present it at NeurIPS OPT 2026.
arxiv.org/abs/2610.11730
BRAInLab retweeted
1) Muon works because it updates a matrix as a matrix. LoRA splits that matrix into A and B, then most optimizers update the factors independently. The induced step on BA can point somewhere quite different. We built LoRA-TSD to put Muon's geometry back where it belongs.
BRAInLab retweeted
馃У Accepted at UAI 2026, @UncertaintyInAI . Distributed training is bottlenecked by communication, so everyone compresses gradients: RandK, QSGD, PermK. But almost every compressor is memory-less. It redraws coordinates from scratch every step, as if history did not exist.
BRAInLab retweeted
1) Happy to share our paper is out at @RealAAAI 2025! Stochastic optimization assumes i.i.d. noise. In RL and distributed training it is not: the noise is correlated across steps. That Markovian case had stayed Euclidean. We bring geometry, acceleration, and optimality. 馃У








