Dara Varam

2 related articles

Subscribe to updates

arXiv Nov 10, 2026
A language model writes an EEG network without a single gradient step: all 2,730 weights by hand, 0.834 balanced accuracy from five subjects
Weight-space programming lets a language model read and edit a trained network's weights directly, and had been shown on game-playing networks and language models. Applied to EEG and ECG models, Claude Opus 5.5 wrote all 2,730 weights of TinyEEGNet with no gradient step and only five practice subjects, reaching 0.834 balanced accuracy on 65 unseen subjects, on par with 0.806 for the same architecture trained on 30 subjects and above 0.704 trained on five; it could not infer a network's task from its weights, nor improve an already well-trained network.
Weight-space programming lets a language model read and edit a trained network's weights directly, and had been shown on game-playing networks and language models. Applied to EEG and ECG models, Claude Opus 5.5 wrote all 2,730 weights of TinyEEGNet with no gradient step and only five practice subjects, reaching 0.834 balanced accuracy on 65 unseen subjects, on par with 0.806 for the same architecture trained on 30 subjects and above 0.704 trained on five; it could not infer a network's task from its weights, nor improve an already well-trained network.
Dara Varam（First author）
Weight-Space Programming Electroencephalography Electrocardiography Claude Opus 5.5 Shortcut Learning
arXiv Sep 29, 2026
PCD pins the primary gradient into the update direction and holds 70.9% accuracy at 90% sparsity on ResNet-34/CIFAR-100 while symmetric multi-objective baselines collapse
The work introduces Priority-Constrained Descent (PCD), a gradient-based framework that anchors on the primary gradient and applies only the minimal Euclidean distortion needed to guarantee each secondary objective a τ-fraction of first-order progress, reporting better per-objective performance and Pareto dominance over symmetric multi-objective methods in structured pruning, unstructured sparsity with low-rankness, and synthetic experiments, with closed-form solutions for two and three objectives and scale invariance.
The work introduces Priority-Constrained Descent (PCD), a gradient-based framework that anchors on the primary gradient and applies only the minimal Euclidean distortion needed to guarantee each secondary objective a τ-fraction of first-order progress, reporting better per-objective performance and Pareto dominance over symmetric multi-objective methods in structured pruning, unstructured sparsity with low-rankness, and synthetic experiments, with closed-form solutions for two and three objectives and scale invariance.
American University of Sharjah
Dara Varam（First author）
Priority-Constrained Descent Multi-Objective Optimization Structured Network Compression Quadratic Program

You’re all caught up

A language model writes an EEG network without a single gradient step: all 2,730 weights by hand, 0.834 balanced accuracy from five subjects

PCD pins the primary gradient into the update direction and holds 70.9% accuracy at 90% sparsity on ResNet-34/CIFAR-100 while symmetric multi-objective baselines collapse