Related papers: Opening the Black Box of Local Projections
Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targeted model, ignoring the internal mechanisms responsible for attack success or failure. Conversely,…
As machine learning systems become more ubiquitous, methods for understanding and interpreting these models become increasingly important. In particular, practitioners are often interested both in what features the model relies on and how…
Efficient simulation is essential for enhancing proactive preparedness for sudden-onset disasters such as earthquakes. Recent advancements in large language models (LLMs) as world models show promise in simulating complex scenarios. This…
Conformal prediction is a popular method to construct prediction intervals with marginal coverage guarantees from black-box machine learning models. In applications with potentially high-impact events, such as flooding or financial crises,…
This chapter first presents a rather personal view of some different aspects of predictability, going in crescendo from simple linear systems to high-dimensional nonlinear systems with stochastic forcing, which exhibit emergent properties…
Hydrocarbon prospect risking is a critical application in geophysics predicting well outcomes from a variety of data including geological, geophysical, and other information modalities. Traditional routines require interpreters to go…
The emergence of tools based on artificial intelligence has also led to the need of producing explanations which are understandable by a human being. In most approaches, the system is considered a black box, making it difficult to generate…
Causal inference and the estimation of causal effects plays a central role in decision-making across many areas, including healthcare and economics. Estimating causal effects typically requires an estimator that is tailored to each problem…
As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical. Classical approaches that assess…
Structured prediction is used in areas such as computer vision and natural language processing to predict structured outputs such as segmentations or parse trees. In these settings, prediction is performed by MAP inference or, equivalently,…
Quantum nonlocality is often judged by violations of Bell-type inequalities for a given state. The computation of such violations is a global task, requiring evaluation of global correlations and subsequent testing against a Bell…
The use of sophisticated machine learning models for critical decision making is faced with a challenge that these models are often applied as a "black-box". This has led to an increased interest in interpretable machine learning, where…
Panel local projection (LP) with fixed-effects (FE) is widely adopted for evaluating the economic consequences of financial crises across countries. This paper highlights a fundamental methodological issue: the presence of the Nickell bias…
Research in both machine learning and psychology suggests that salient examples can help humans to interpret learning models. To this end, we take a novel look at black box interpretation of test predictions in terms of training examples.…
The growing complexity of machine learning and deep learning models has led to an increased reliance on opaque "black box" systems, making it difficult to understand the rationale behind predictions. This lack of transparency is…
In science and medicine, model interpretations may be reported as discoveries of natural phenomena or used to guide patient treatments. In such high-stakes tasks, false discoveries may lead investigators astray. These applications would…
Strategies based on Explainable Artificial Intelligence (XAI) have promoted better human interpretability of the results of black box models. This opens up the possibility of questioning whether explanations created by XAI methods meet…
Machine learning models are becoming increasingly popular in different types of settings. This is mainly caused by their ability to achieve a level of predictive performance that is hard to match by human experts in this new era of big…
We initiate a novel approach to explain the predictions and out of sample performance of random forest (RF) regression and classification models by exploiting the fact that any RF can be mathematically formulated as an adaptive weighted K…
Range-based volatility estimators are widely used in financial econometrics to quantify risk and market stress, yet their application to local commodity markets remains limited. This paper shows how open-high--low-close (OHLC) volatility…