Skip to content
Tagged articles

computational complexity

4 articles · Page 1 of 1
AI Frontier Lectures
AI Frontier Lectures
Nov 7, 2026 · Artificial Intelligence

AI Proves 2008 Aaronson-Ambainis Quantum Conjecture Using Unpublished Anthropic Model

Physical Superintelligence's AI system, powered by an unpublished Anthropic model, formally proved the 2008 Aaronson-Ambainis conjecture in three days, showing quantum computers gain at most polynomial speedup over classical computers for random inputs, with a 7th-power bound verified in Lean.

AI-assisted proofAaronson-Ambainis conjectureAnthropic
0 likes · 6 min read
AI Proves 2008 Aaronson-Ambainis Quantum Conjecture Using Unpublished Anthropic Model
SuanNi
SuanNi
Apr 30, 2026 · Artificial Intelligence

Why Transformers Are Naturally Succinct: Insights from the ICLR Best Paper

The ICLR 2026 best paper reveals that Transformers achieve extreme succinctness—encoding complex concepts with exponentially fewer symbols than RNNs—while proving that analyzing or verifying such models incurs EXPSPACE‑complete computational costs.

EXPSPACESuccinctnessTheoretical AI
0 likes · 8 min read
Why Transformers Are Naturally Succinct: Insights from the ICLR Best Paper
DataFunTalk
DataFunTalk
Jan 20, 2021 · Artificial Intelligence

Techniques for Reducing the Computational Complexity of Large-Scale Graph Neural Networks

This article presents an overview of graph neural networks, explains their computational framework, analyzes space and time complexities, and proposes ten practical strategies—including edge avoidance, dimensionality reduction, selective iteration, memory baking, distillation, partitioning, sparse computation, routing, and cross-sample feature sharing—to significantly lower the cost of large‑scale GNN processing.

computational complexitydeep learninglarge-scale
0 likes · 14 min read
Techniques for Reducing the Computational Complexity of Large-Scale Graph Neural Networks