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.
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.
Study models opaque financial markets using multi-agent simulation.
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…
Protocol assesses better model among two opaque models with minimal interaction.
Survey connects XAI and surrogate modeling for better understanding of complex systems.
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…
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…
The thesis tackles two stochastic control problems in capital structure and portfolio choice.
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…
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 …
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…
SMILE improves explainability of machine learning models.
This paper combines LLMs with RL for better trading strategies.
Tuning machine learning models, particularly deep learning architectures, is a complex process. Automated hyperparameter tuning algorithms often depend on specific optimization metrics. However, in many situations, a developer trades one metric against another: accuracy versus overfitting, precision versus recall, smal…
Survey on making machine learning models more understandable.
This paper studies generic properties of connections on vector bundles, solving cohomological equations and proving opaque connections.
Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using Singular Value Decomposition (SVD), may incur loss of corpus information. In addi…
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…
Bayesian framework improves survival prediction accuracy and uncertainty quantification.
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…
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…
Automated feature engineering improves interpretable models without manual work.
FAST-DAD distills complex ensemble models into faster, more accurate individual models.
Gaussian process models simplify neural network behavior for easier understanding.
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…
AI-Interpret transforms opaque policies into simple, interpretable decision rules.
A new method uses conformal prediction to create reliable confidence masks for image super-resolution.
Posterior Matching enables VAEs to model arbitrary conditional densities.
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…
Dagma-DCE improves causal discovery with interpretable measures and open-source code.
dalex simplifies model exploration and fairness for Python developers.
Two new methods assess feature importance for fairness in machine learning models.
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…
BaMANI uses ensemble learning to improve Bayesian network inference.
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…
The study assesses sensitivity to prior choices in Bayesian nonparametric models.
KaCGM models provide transparent causal inference from tabular data.
EBMs become opaque in high dimensions; LASSO sparsifies them.
New approach uses prior knowledge to improve neural network representations.
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…