A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
TaylorPODA uses Taylor expansions to improve feature attributions for opaque models.
Study models opaque financial markets using multi-agent simulation.
LIMEADE improves AI advice for opaque models, enhancing accuracy and user satisfaction.
A Bloom filter approach combined with Transformer models improves accuracy for machine learning tasks on opaque IDs.
New method refines model-free evaluation of complex machine learning models.
Paper shows how to quantify uncertainty in medical ML models.
The paper tests semantic importance in opaque models using betting.
New method estimates model risk without knowing function class.
Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little investigation into interpreting what specific trends and patterns an active learning st…
Representations learnt through deep neural networks tend to be highly informative, but opaque in terms of what information they learn to encode. We introduce an approach to probabilistic modelling that learns to represent data with two separate deep representations: an invariant representation that encodes the informat…
FAST-DAD distills complex ensemble models into faster, more accurate individual models.
Given key performance indicators collected with fine granularity as time series, our aim is to predict and explain failures in storage environments. Although explainable predictive modeling based on spiky telemetry data is key in many domains, current approaches cannot tackle this problem. Deep learning methods suitabl…
SMILE improves explainability of machine learning models.
New approach uses prior knowledge to improve neural network representations.
Complex black-box predictive models may have high accuracy, but opacity causes problems like lack of trust, lack of stability, sensitivity to concept drift. On the other hand, interpretable models require more work related to feature engineering, which is very time consuming. Can we train interpretable and accurate mod…
Thanks to the availability of large scale digital datasets and massive amounts of computational power, deep learning algorithms can learn representations of data by exploiting multiple levels of abstraction. These machine learning methods have greatly improved the state-of-the-art in many challenging cognitive tasks, s…
Black-box risk scoring models permeate our lives, yet are typically proprietary or opaque. We propose Distill-and-Compare, a model distillation and comparison approach to audit such models. To gain insight into black-box models, we treat them as teachers, training transparent student models to mimic the risk scores ass…
A new method uses conformal prediction to create reliable confidence masks for image super-resolution.
Protocol assesses better model among two opaque models with minimal interaction.
KaCGM models provide transparent causal inference from tabular data.
A new framework for fair representation learning using correction vectors.
Supervised Machine Learning (SML) algorithms such as Gradient Boosting, Random Forest, and Neural Networks have become popular in recent years due to their increased predictive performance over traditional statistical methods. This is especially true with large data sets (millions or more observations and hundreds to t…
Cameras are an essential part of sensor suite in autonomous driving. Surround-view cameras are directly exposed to external environment and are vulnerable to get soiled. Cameras have a much higher degradation in performance due to soiling compared to other sensors. Thus it is critical to accurately detect soiling on th…
Survey connects XAI and surrogate modeling for better understanding of complex systems.
Recently, deep learning becomes the main focus of machine learning research and has greatly impacted many important fields. However, deep learning is criticized for lack of interpretability. As a successful unsupervised model in deep learning, the autoencoder embraces a wide spectrum of applications, yet it suffers fro…
This paper studies generic properties of connections on vector bundles, solving cohomological equations and proving opaque connections.
Evaluation of deep reinforcement learning (RL) is inherently challenging. In particular, learned policies are largely opaque, and hypotheses about the behavior of deep RL agents are difficult to test in black-box environments. Considerable effort has gone into addressing opacity, but almost no effort has been devoted t…
Explainable Artificial Intelligence (XAI)has received a great deal of attention recently. Explainability is being presented as a remedy for the distrust of complex and opaque models. Model agnostic methods such as LIME, SHAP, or Break Down promise instance-level interpretability for any complex machine learning model. …
Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN. We develop…
Bayesian framework improves survival prediction accuracy and uncertainty quantification.
DORA analyzes deep neural networks' internal representations to detect spurious correlations.
AI-Interpret transforms opaque policies into simple, interpretable decision rules.
dalex simplifies model exploration and fairness for Python developers.
Due to the capability of deep learning to perform well in high dimensional problems, deep reinforcement learning agents perform well in challenging tasks such as Atari 2600 games. However, clearly explaining why a certain action is taken by the agent can be as important as the decision itself. Deep reinforcement learni…
Paper introduces Native Guide for generating time series counterfactual explanations.
Tree-Query uses LLMs to discover causal relationships in a transparent, interpretable manner.
Bayesian symbolic regression uncovers missing physics from data with uncertainty quantification.
The thesis tackles two stochastic control problems in capital structure and portfolio choice.
Although deep learning models have been successfully applied to a variety of tasks, due to the millions of parameters, they are becoming increasingly opaque and complex. In order to establish trust for their widespread commercial use, it is important to formalize a principled framework to reason over these models. In t…
This paper provides a guide to feature importance methods for better scientific inference.
Although neural networks can achieve very high predictive performance on various different tasks such as image recognition or natural language processing, they are often considered as opaque "black boxes". The difficulty of interpreting the predictions of a neural network often prevents its use in fields where explaina…
Posterior Matching enables VAEs to model arbitrary conditional densities.
Automated feature engineering improves interpretable models without manual work.
A reliable controller is critical and essential for the execution of safe and smooth maneuvers of an autonomous vehicle.The controller must be robust to external disturbances, such as road surface, weather, and wind conditions, and so on.It also needs to deal with the internal parametric variations of vehicle sub-syste…
With the advent of highly predictive but opaque deep learning models, it has become more important than ever to understand and explain the predictions of such models. Existing approaches define interpretability as the inverse of complexity and achieve interpretability at the cost of accuracy. This introduces a risk of …
Model-Based Offline Planning (MBOP) learns models from offline data to control systems directly.
Study highlights how lazy data practices in fair ML research can unfairly impact minority groups.
The paper advocates for interpretable, accountable, reproducible machine learning in medicine.