Constraining neural network partial dependence to match domain-knowledge functional forms during training improves predictive accuracy, data efficiency, and explanation faithfulness on regression problems.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
First detailed breakdown of vLLM startup into six CPU-bound steps with scaling trends yields a lightweight analytical model that predicts latency for given hardware configurations.
The paper defines algorithmic contestability as identifying evidence to overturn potentially incorrect decisions and identifies three types of such evidence that make decisions normatively indefensible under the decision maker's standards.
Media sentiment indicators from Canadian news, when added to a New Keynesian model with endogenous central-bank response, improve out-of-sample forecasts and account for part of monetary-policy propagation to output and prices.
Some opacity in black hole imaging methods is compatible with reliable inference under specified conditions, but GRMHD models of Sgr A* exhibit problematic opacity that signals model limitations.
citing papers explorer
-
Steering Neural Network Training through Interpretable Constraints Based on Partial Dependence
Constraining neural network partial dependence to match domain-knowledge functional forms during training improves predictive accuracy, data efficiency, and explanation faithfulness on regression problems.
-
Breaking the Ice: Analyzing Cold Start Latency in vLLM
First detailed breakdown of vLLM startup into six CPU-bound steps with scaling trends yields a lightweight analytical model that predicts latency for given hardware configurations.
-
Explainable AI Isn't Enough! Rethinking Algorithmic Contestability
The paper defines algorithmic contestability as identifying evidence to overturn potentially incorrect decisions and identifies three types of such evidence that make decisions normatively indefensible under the decision maker's standards.
-
Monetary Policy in the Media Spotlight: Sentiments, Signals, and Economic Impact
Media sentiment indicators from Canadian news, when added to a New Keynesian model with endogenous central-bank response, improve out-of-sample forecasts and account for part of monetary-policy propagation to output and prices.
-
Black Boxes in Black Hole Imaging
Some opacity in black hole imaging methods is compatible with reliable inference under specified conditions, but GRMHD models of Sgr A* exhibit problematic opacity that signals model limitations.