awni.bsky.social
@awni.bsky.social
phd student @ yale statistics & data science
studying the foundations of machine intelligence
awni.xyz
studying the foundations of machine intelligence
awni.xyz
🧪 Theory meets Practice
We empirically validate our theory’s predictions in simple settings where the CoT information can be computed exactly.
We find that the theory closely predicts the sample-efficiency gains.
[8/n]
We empirically validate our theory’s predictions in simple settings where the CoT information can be computed exactly.
We find that the theory closely predicts the sample-efficiency gains.
[8/n]
November 25, 2025 at 4:27 AM
🧪 Theory meets Practice
We empirically validate our theory’s predictions in simple settings where the CoT information can be computed exactly.
We find that the theory closely predicts the sample-efficiency gains.
[8/n]
We empirically validate our theory’s predictions in simple settings where the CoT information can be computed exactly.
We find that the theory closely predicts the sample-efficiency gains.
[8/n]
🧮 The Theory
To distinguish between hypotheses with error ε, classical theory tells us we need roughly O(1/ε) samples.
We prove that under CoT supervision, the sample complexity improves to O(1/CoTInfo(ε)).
[5/n]
To distinguish between hypotheses with error ε, classical theory tells us we need roughly O(1/ε) samples.
We prove that under CoT supervision, the sample complexity improves to O(1/CoTInfo(ε)).
[5/n]
November 25, 2025 at 4:27 AM
🧮 The Theory
To distinguish between hypotheses with error ε, classical theory tells us we need roughly O(1/ε) samples.
We prove that under CoT supervision, the sample complexity improves to O(1/CoTInfo(ε)).
[5/n]
To distinguish between hypotheses with error ε, classical theory tells us we need roughly O(1/ε) samples.
We prove that under CoT supervision, the sample complexity improves to O(1/CoTInfo(ε)).
[5/n]
🧠 The Insight: CoT supervision doesn’t just tell the model what to predict; it constrains how it thinks.
We formalize this by introducing the “CoT Information”: a measure of the extra discriminative power gained by observing the reasoning trace, not just the label.
[4/n]
We formalize this by introducing the “CoT Information”: a measure of the extra discriminative power gained by observing the reasoning trace, not just the label.
[4/n]
November 25, 2025 at 4:27 AM
🧠 The Insight: CoT supervision doesn’t just tell the model what to predict; it constrains how it thinks.
We formalize this by introducing the “CoT Information”: a measure of the extra discriminative power gained by observing the reasoning trace, not just the label.
[4/n]
We formalize this by introducing the “CoT Information”: a measure of the extra discriminative power gained by observing the reasoning trace, not just the label.
[4/n]
🌟🔗 Spotlight #NeurIPS2025 Paper on the Foundations of Chain-of-Thought Learning 🔗🌟
Excited to share our work developing a learning-theoretic account of the statistical advantage of chain-of-thought supervision in reasoning systems!
Blog: awni.xyz/cot-info
👇🧵
[1/n]
Excited to share our work developing a learning-theoretic account of the statistical advantage of chain-of-thought supervision in reasoning systems!
Blog: awni.xyz/cot-info
👇🧵
[1/n]
November 25, 2025 at 4:27 AM
🌟🔗 Spotlight #NeurIPS2025 Paper on the Foundations of Chain-of-Thought Learning 🔗🌟
Excited to share our work developing a learning-theoretic account of the statistical advantage of chain-of-thought supervision in reasoning systems!
Blog: awni.xyz/cot-info
👇🧵
[1/n]
Excited to share our work developing a learning-theoretic account of the statistical advantage of chain-of-thought supervision in reasoning systems!
Blog: awni.xyz/cot-info
👇🧵
[1/n]