Home Knowledge Base STE

STE

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Beyond Discreteness: Sample Complexity Analysis of Straight-Through Estimator for 1-bit Quantization

arXiv:2505.18113v2 Announce Type: replace Abstract: Training quantized neural networks requires addressing the non-differentiable and discrete nature of the underlying optimization problem. To tackle this challenge, the straight-through estimator (STE) has become the most widely adopted heuristic, allowing backpropagation through discrete operations by introducing biased yet valid surrogate gradients. However, its theoretical properties remain largely unexplored, with few existing analyses...

arXiv CS 8d ago

Sensitivity as a Double-Edged Sword: A Trade-off Between Discriminability and Adversarial Robustness

Announce Type: new Abstract: Modern neural networks are highly susceptible to adversarial perturbations. In this work, we identify that part of this vulnerability stems from the sensitivity of the widely used fully connected (FC) classifiers to such perturbations. In contrast, simple $\ell_2$ distance-based classifiers exhibit significantly greater robustness.

arXiv CS 8d ago

DOT-MoE: Differentiable Optimal Transport for MoEfication

arXiv:2606.01666v1 Announce Type: new Abstract: The scaling of Large Language Models (LLMs) has driven significant performance gains but created substantial challenges in inference efficiency. While Mixture of Experts (MoEs) architectures address this by decoupling model size from inference cost, training MoEs from scratch is often unstable and compute intensive. Conversion of pre-trained dense models into sparse MoEs has emerged as an alternative solution; however, existing methods...

arXiv CS 8d ago

An unfinished reckoning with police violence: Community data show ongoing systemic racism

An unfinished reckoning with police violence: Community data show ongoing systemic racism Gaby Clark Scientific Editor Andrew Zinin Lead Editor It's been roughly six years since the killing of George Floyd in Minneapolis sparked a global conversation about anti-Black police violence and the excessive use of police force against Black and Indigenous communities.

Phys.org 6d ago