Adam M. Smith

Artificial Intelligence · with Brown · 2020

A researcher in the Science corpus: 1 paper; trusts 4 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 26 citations into it

Whom Adam M. Smith trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Vitaly Feldman
2. Cynthia Dwork
3. Nicholas Carlini

Papers from Adam M. Smith's perspective

Ordered by how strongly the researchers Adam M. Smith trusts endorse each paper. Same corpus, a different order for every researcher.

1. Understanding deep learning requires rethinking generalization
2. Language Models are Few-Shot Learners (Neural Information Processing Systems)
3. Revealing information while preserving privacy
4. Calibrating Noise to Sensitivity in Private Data Analysis
5. Membership Inference Attacks Against Machine Learning Models
6. The information bottleneck method
7. What Can We Learn Privately?
8. Does learning require memorization? a short tale about a long tail
9. Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
10. Practical privacy: the SuLQ framework

Their papers

• When is memorization of irrelevant training data necessary for high-accuracy learning? (2020) — 130 citations