Moscow Institute of Physics and Technology

The Burer–Monteiro factorized objective for low-rank matrix minimization is shown to be generalized smooth with exponent 2/3, and adaptive gradient descent and SafeAdam built on that property match or beat Dyn-NoLips on SymNMF text and image benchmarks without tuning relative-smoothness kernel parameters.

The Burer–Monteiro factorized objective for low-rank matrix minimization is shown to be generalized smooth with exponent 2/3, and adaptive gradient descent and SafeAdam built on that property match or beat Dyn-NoLips on SymNMF text and image benchmarks without tuning relative-smoothness kernel parameters.

A multi-agent large language model framework confines neural network tuning to designated functional blocks while the overall network structure stays fixed. Such key components were previously chosen by hand, and existing agent systems either optimize the entire machine learning script or build a network from a text description. With analyst, coder, and recorder roles plus a sandboxed environment and an experiment log, the framework beats its baselines on five tasks: MNIST classification accuracy rises 13 percentage points, digits 6 points, the relative error on the single-soliton generalized nonlinear Schrödinger equation drops about 2491-fold, the conservation error drops about 325-fold in the selected run, and mass drift on the Kuramoto–Sivashinsky problem drops 14-fold.

A multi-agent large language model framework confines neural network tuning to designated functional blocks while the overall network structure stays fixed. Such key components were previously chosen by hand, and existing agent systems either optimize the entire machine learning script or build a network from a text description. With analyst, coder, and recorder roles plus a sandboxed environment and an experiment log, the framework beats its baselines on five tasks: MNIST classification accuracy rises 13 percentage points, digits 6 points, the relative error on the single-soliton generalized nonlinear Schrödinger equation drops about 2491-fold, the conservation error drops about 325-fold in the selected run, and mass drift on the Kuramoto–Sivashinsky problem drops 14-fold.