View PDF ↗
PDF Viewer
Open Full PDF

BUILDER'S SANDBOX

Build This Paper

Use an AI coding agent to implement this research.

OpenAI Codex
OpenAI CodexAI Agent

Lightweight coding agent in your terminal.

Claude Code
Claude CodeAI Agent

Agentic coding tool for terminal workflows.

AntiGravity IDE
AntiGravity IDEScaffolding

AI agent mindset installer and workflow scaffolder.

Cursor
CursorIDE

AI-first code editor built on VS Code.

VS Code
VS CodeIDE

Free, open-source editor by Microsoft.

Estimated $9K - $13K over 6-10 weeks.

See exactly what it costs to build this -- with 3 comparable funded startups.

7-day free trial. Cancel anytime.

Discover the researchers behind this paper and find similar experts.

7-day free trial. Cancel anytime.

References (21)

[1]
Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMs
2025Hancheng Min, René Vidal
[2]
Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling
2023Mingze Wang, Zeping Min et al.
[3]
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks
2023Spencer Frei, Gal Vardi et al.
[4]
Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces
2023Odelia Melamed, Gilad Yehudai et al.
[5]
Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data
2022Spencer Frei, Gal Vardi et al.
[6]
Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias
2021Kaifeng Lyu, Zhiyuan Li et al.
[7]
Continuous vs. Discrete Optimization of Deep Neural Networks
2021Omer Elkabetz, Nadav Cohen
[8]
Fast Margin Maximization via Dual Acceleration
2021Ziwei Ji, N. Srebro et al.
[9]
Towards Understanding Learning in Neural Networks with Linear Teachers
2021Roei Sarussi, Alon Brutzkus et al.
[10]
Directional convergence and alignment in deep learning
2020Ziwei Ji, Matus Telgarsky
[11]
Gradient Descent Maximizes the Margin of Homogeneous Neural Networks
2019Kaifeng Lyu, Jian Li
[12]
Characterizing the implicit bias via a primal-dual analysis
2019Ziwei Ji, Matus Telgarsky
[13]
Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate
2018M. S. Nacson, N. Srebro et al.
[14]
Risk and parameter convergence of logistic regression
2018Ziwei Ji, Matus Telgarsky
[15]
Convergence of Gradient Descent on Separable Data
2018M. S. Nacson, J. Lee et al.
[16]
The Implicit Bias of Gradient Descent on Separable Data
2017Daniel Soudry, Elad Hoffer et al.
[17]
The Zero Set of a Real Analytic Function
2015B. Mityagin
[18]
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
2015Kaiming He, X. Zhang et al.
[19]
Intriguing properties of neural networks
2013Christian Szegedy, Wojciech Zaremba et al.
[20]
Evasion Attacks against Machine Learning at Test Time
2013B. Biggio, Igino Corona et al.

Showing 20 of 21 references

Founder's Pitch

"Develop algorithms to improve the convergence rate of Gradient Descent in non-linear neural networks for better adversarial robustness."

Optimization AlgorithmsScore: 2View PDF ↗

Commercial Viability Breakdown

0-10 scale

High Potential

1/4 signals

2.5

Quick Build

0/4 signals

0

Series A Potential

0/4 signals

0

Sources used for this analysis

arXiv Paper

Full-text PDF analysis of the research paper

GitHub Repository

Code availability, stars, and contributor activity

Citation Network

Semantic Scholar citations and co-citation patterns

Community Predictions

Crowd-sourced unicorn probability assessments

Analysis model: GPT-4o · Last scored: 3/2/2026

Explore the full citation network and related research.

7-day free trial. Cancel anytime.

Understand the commercial significance and market impact.

7-day free trial. Cancel anytime.

Get detailed profiles of the research team.

7-day free trial. Cancel anytime.