Research map / Learning theory and algorithms / Prediction and decision losses

Position: A Critical Perspective on The Value in Studying Deep Learning Phenomena

ICML 2025 · Learning theory and algorithms › Prediction and decision losses · approach: Provable post-hoc explanations

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

A position paper arguing critically about the scientific value of studying deep learning phenomena, based only on its title and venue since the full text is unavailable.

Problem

Whether and how studying empirical deep learning phenomena (as opposed to engineering outcomes) produces scientific value; the abstract was not available, so the specific problem framing is not stated.

Approach

Not stated in the available information; the title indicates a critical perspective on the value of phenomena-focused deep learning research.

Limitations

• Full text unavailable; abstract content not provided, so claims cannot be verified.

Closest papers by meaning

• Position: Not All Explanations for Deep Learning Phenomena Are Equally Valuable (ICML 2025 · similarity 0.84)
• Deep Learning Through the Lens of Example Difficulty (NeurIPS 2021 · similarity 0.82)
• Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory (ICLR 2025 · similarity 0.80)
• Deep Value Benchmark: Measuring Whether Models Generalize Deep values or Shallow Preferences (NeurIPS 2025 · similarity 0.80)
• Great Minds Think Alike: The Universal Convergence Trend of Input Salience (NeurIPS 2024 · similarity 0.80)
• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond (NeurIPS 2024 · similarity 0.79)