#regression-models News & Analysis

4 articles tagged with #regression-models. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AINeutralarXiv – CS AI · Jun 27/10

🧠

Shortcut to Nowhere: Demystifying Deep Spurious Regression

Researchers introduce Deep Spurious Regression (DSR), a framework addressing how machine learning models rely on unreliable correlations when predicting continuous values rather than categorical labels. The work identifies a critical gap in AI robustness research, which has largely focused on classification tasks, and proposes techniques to improve model generalization across different data distributions by calibrating feature and label spaces.

AIBearisharXiv – CS AI · Mar 37/104

🧠

Stealthy Poisoning Attacks Bypass Defenses in Regression Settings

Researchers have developed new stealthy poisoning attacks that can bypass current defenses in regression models used across industrial and scientific applications. The study introduces BayesClean, a novel defense mechanism that better protects against these sophisticated attacks when poisoning attempts are significant.

AIBullishGoogle Research Blog · Jul 297/106

🧠

Simulating large systems with Regression Language Models

The article discusses the use of Regression Language Models for simulating large-scale systems in the context of generative AI. This represents an advancement in AI modeling capabilities that could have implications for various computational applications.

AIBullisharXiv – CS AI · May 286/10

🧠

Regression Language Models for Code

Researchers have developed Regression Language Models (RLMs) that use frozen LLM encoders to predict numeric code execution outcomes across multiple programming languages and domains. A 300M parameter model demonstrates strong performance predicting memory footprint, GPU latency, neural network accuracy, and hardware platform performance without domain-specific feature engineering.