Mindful Modeler

Mindful Modeler focuses on enhancing machine learning practices through statistical thinking, critical data analysis, and model interpretability. It delves into methods like conformal prediction, quantile regression, and handling imbalanced data, emphasizing the importance of uncertainty estimation, thoughtful data treatment, and leveraging inductive biases for resilient, informative modeling.

Machine Learning Statistical Modeling Data Analysis Model Interpretability Uncertainty Quantification Research and Development Career Development Writing and Documentation

The hottest Substack posts of Mindful Modeler

And their main takeaways

Defending machine learning in a room full of old-school statisticians

299 implied HN points • 27 Jun 23
🕹 Technology Machine Learning Statistics Modeling
  1. Be mindful of your modeling mindset and be open to exploring other modeling cultures beyond your current beliefs.
  2. Recognize that differences in modeling mindsets are deeply rooted in culture and background, influencing how individuals approach statistical modeling.
  3. Interpretability remains a significant concern for modelers, especially in the context of machine learning advancements, although progress has been made in providing tools for better understanding models.

Use Interpretability to Justify Your Model

199 implied HN points • 19 Dec 23
🕹 Technology Machine Learning
  1. Performance of a machine learning model is not always enough to justify its use; interpretability is crucial for justification.
  2. Interpretability plays a key role in justifying a model by making people trust the model and its predictions.
  3. Different interpretation approaches may be needed for justifying models to different audiences and contexts, understanding the roles of creators, operators, executors, decision-subjects, and examiners.

What A Horse Can Tell Us About Machine Learning

279 implied HN points • 10 Oct 23
🕹 Technology Machine Learning Artificial Intelligence Data Analysis Predictive Modeling
  1. Animals like horses and machines can appear clever by relying on cues and shortcuts, rather than true understanding.
  2. When designing or evaluating machine learning models, watch out for 'Clever Hans Predictors' that rely on spurious correlations.
  3. To spot potential Clever Hans Predictors, look for unexpectedly good model performance, apply causal thinking, examine data closely, and use interpretation methods to investigate model behavior.

The Galactic Guide to SHAP Values

279 implied HN points • 25 Jul 23
🕹 Technology Machine Learning Data interpretation
  1. SHAP values are like forces acting on a planet in a universe analogy, helping explain machine learning model predictions
  2. Each feature in a machine learning model contributes as a force, with SHAP values showing how they impact the prediction
  3. SHAP values aim to maintain the prediction's equilibrium by considering all forces, revealing which features are vital

The Statistician Who Loved Machine Learning

279 implied HN points • 23 May 23
🕹 Technology Machine Learning Statistics Modeling Algorithms
  1. Leo Breiman emphasized the importance of both data modeling culture and algorithmic modeling culture in statistical modeling.
  2. Breiman advocated for being problem-focused over solution-focused, encouraging modelers to choose the appropriate mindset based on the task at hand.
  3. Understanding various modeling mindsets, such as statistical inference and machine learning, is crucial for effective modeling.
Get a weekly roundup of the best Substack posts, by hacker news affinity:

Reshaping a Book

239 implied HN points • 04 Jul 23
🚌 Education Writing Feedback Improvement Collaboration
  1. Accepting feedback is crucial for improving your work. It can lead to significant changes and enhancements in your projects.
  2. Collaborating with beta readers and working with an editor can provide valuable insights and help spot issues that may be overlooked.
  3. Separating theory, implementation, and application in writing can improve the flow and clarity of your content. Using smaller building blocks and setting learning goals for each unit can lead to a more coherent narrative.

Why SHAP needs to be estimated

239 implied HN points • 11 Jul 23
🕹 Technology Machine Learning Interpretation Estimation Python
  1. SHAP values used in machine learning need to be estimated rather than calculated exactly, based on the concept of Shapley values from game theory.
  2. Estimating SHAP values is necessary due to the exponential increase in possible coalitions with a high number of features, requiring sampling techniques.
  3. The complexity of working with distributions in machine learning models necessitates the estimation of SHAP values using techniques like Monte Carlo integration.

Simplify Your Writing Process with Quarto

319 implied HN points • 11 Apr 23
🕹 Technology Technical Writing
  1. Use Quarto to simplify writing processes by integrating code with text in markdown format.
  2. Ensure your writing is version-controlled for peace of mind and use one source format for multiple outputs.
  3. Quarto allows you to write in a markdown file format (.qmd), which can be easily converted to various forms like ebooks, reports, or websites.

Uncertainty beyond the model

239 implied HN points • 13 Jun 23
🔬 Science Machine Learning
  1. Data uncertainty is prevalent in real-world data and should not be overlooked, including variables, errors in measurements, and missing data.
  2. Deployment uncertainty arises when machine learning models encounter new data, leading to potential performance issues due to distribution shifts.
  3. Consider beyond aleatoric and epistemic uncertainties and also address data and deployment uncertainties to improve model robustness.

Machine learning eats up science

219 implied HN points • 18 Oct 23
🔬 Science Machine Learning Research Technology Book Writing Data Analysis
  1. Research papers increasingly focus on AI and ML, indicating a growing trend in the scientific community.
  2. AI and ML offer significant benefits in terms of saving time, automating tasks, and enabling research.
  3. Challenges like bias, fraud, and lack of reproducibility persist, with a major concern being the reliance on pattern recognition over understanding in ML and AI.

E-Mail Course On Conformal Prediction

479 implied HN points • 13 Dec 22
🚌 Education Predictive Modeling Data science Machine Learning Research
  1. Conformal prediction turns point predictions into prediction sets with a probability guarantee of covering the true outcome, working for any model without requiring a distribution assumption.
  2. The 5-week email course on conformal prediction offers a free, convenient way to learn about this uncertainty quantification method.
  3. Resources like Valeriy's list on conformal prediction and an academic introduction paper can be helpful for diving into and understanding conformal prediction.

Should we stop interpreting ML models because XAI methods are imperfect?

199 implied HN points • 31 Oct 23
🕹 Technology Machine Learning Interpretability Neural Networks Modeling
  1. Don't let a pursuit of perfection in interpreting ML models hinder progress. It's important to be pragmatic and make decisions even in the face of imperfect methods.
  2. Consider the balance of benefits and risks when interpreting ML models. Imperfect methods can still provide valuable insights despite their limitations.
  3. While aiming for improvements in interpretability methods, it's practical to use the existing imperfect methods that offer a net benefit in practice.

Interpreting Machine Learning Models With SHAP is published 🥳

199 implied HN points • 01 Aug 23
🕹 Technology Machine Learning Interpretability Python Books Podcasts
  1. SHAP can explain individual predictions and provide interpretations of average model behavior for any model type and data format.
  2. There's a need for a comprehensive guide like the book to navigate the evolving SHAP ecosystem with updated information and practical examples.
  3. The book dives into the theory, application, and various estimation methods of SHAP values, offering a one-stop resource for mastering machine learning model interpretability.

Week #2: Intuition Behind Conformal Prediction

379 implied HN points • 27 Dec 22
🔬 Science Data science Machine Learning Statistics Training Model Evaluation
  1. Conformal prediction for classification works by ordering predictions from certain to uncertain, dividing them based on a user-defined confidence level.
  2. Conformal prediction consists of three main steps: training, calibration, and prediction, following a similar recipe across different algorithms.
  3. Different resampling strategies like k-fold cross-splitting and jackknife are used in conformal prediction, offering a balance between computation cost and prediction accuracy.

Feature Selection And Feature Importance: How Are They Related?

299 implied HN points • 28 Feb 23
🕹 Technology Machine Learning Interpretability
  1. Feature selection and feature importance are different steps in modeling with different goals, but they are complementary. Getting feature selection right can enhance interpretability.
  2. Feature selection aims to reduce the number of features used in the model to improve predictive performance, speed up training, enhance comprehensibility, and reduce costs.
  3. Feature importance involves ranking and quantifying the contribution of features to model predictions, aiding in understanding model behavior, auditing, debugging, feature engineering, and comprehending the modeled phenomenon.

Explore Your Modeling Mindset With A Quiz

179 implied HN points • 20 Jun 23
🕹 Technology Modeling Web Development Machine Learning Programming
  1. Modeling assumptions affect how the model can be used. For instance, causal considerations lead to causal claims.
  2. Revisiting and understanding our modeling assumptions can help us tackle problems more effectively, beyond our usual mindset.
  3. Creating simple static websites can be made easier with tools like GPT-4, especially if you have some understanding of HTML, CSS, and JavaScript.

Correlation Can Ruin Interpretability

479 implied HN points • 20 Sep 22
🔬 Science Data interpretation Correlation Visualization
  1. Correlation between features can significantly impact the interpretability of machine learning models, both technically and philosophically.
  2. Identifying and addressing correlation issues is crucial for accurate model interpretation. Techniques include grouping correlated features, decorrelation methods like PCA, feature selection, causal modeling, and conditional interpretation.
  3. Entanglement of interpretation due to correlation makes it challenging to isolate the impact of individual features in machine learning models.

Can you explain GPT with ... GPT?

199 implied HN points • 16 May 23
🕹 Technology Neural Networks Interpretability Modeling Language Models AI Ethics
  1. OpenAI experimented with using GPT-4 to interpret the functionality of neurons in GPT-2, showcasing a unique approach to understanding neural networks.
  2. The process involved analyzing activations for various input texts, selecting specific texts to explain neuron activations, and evaluating the accuracy of these explanations.
  3. Interpreting complex models like LLMs with other complex models, such as using GPT-4 to understand GPT-2, presents challenges but offers a method to evaluate and improve interpretability.

The SHAP Book is Available in Print 🥳

159 implied HN points • 12 Sep 23
🕹 Technology Machine Learning Explainable AI Book
  1. SHAP is an explainable AI technique that computes Shapley values for machine learning predictions, attributing predicted value among features fairly.
  2. SHAP is versatile and model-agnostic, working with any model type from linear regression to deep learning, and handling various data formats like tabular, image, or text.
  3. The SHAP Book offers a comprehensive guide to mastering the theory and application of SHAP, suitable for data scientists, statisticians, machine learners, and those familiar with Python.

From bare-bones to holistic machine learning

159 implied HN points • 08 Aug 23
🕹 Technology Machine Learning Modeling Interpretability Data Tools
  1. Machine learning can range from simple, bare-bones tasks to more complex, holistic approaches.
  2. In bare-bones machine learning, the modeling choices are defined, making it about the model's performance and tuning.
  3. Holistic machine learning involves designing the model to connect with the larger context, considering factors like uncertainty, interpretability, and shifts in distribution.

5 questions to categorize machine learning interpretability approaches

419 implied HN points • 13 Sep 22
🕹 Technology Machine Learning
  1. Machine learning interpretability approaches can be categorized using 5 key questions, such as whether they are point-wise or global interpretations.
  2. Interpretability methods can be either interpretable by design or require post-hoc interpretation, with implications for ease of understanding the model.
  3. Some explanation methods generate interpretable models, while others do not, emphasizing the importance of understanding the nature of the explanation outcome.

Week #3: Conformal Prediction For Regression

279 implied HN points • 03 Jan 23
🔬 Science Regression Modeling
  1. In regression, conformal prediction can turn point predictions into prediction intervals with guarantees of future observation coverage.
  2. Starting from point predictions or non-conformal intervals from quantile regression are two common approaches to creating prediction intervals.
  3. Conformalized mean regression and conformalized quantile regression are two techniques to generate prediction intervals in regression models.

10 ways to estimate SHAP

119 implied HN points • 18 Jul 23
🕹 Technology AI Machine Learning Explainable AI Neural Networks
  1. SHAP values are estimated using various methods due to computational constraints
  2. Estimation methods include exact explainer, sampling explainer, permutation explainer, and more to attribute model predictions to features
  3. The `shap` package implements multiple estimation methods, with defaults based on the type of data and model

You Can Break A Predictive Model By Using It - How To Spot And Fix Performative Prediction

299 implied HN points • 27 Sep 22
🕹 Technology AI Data science Machine Learning Predictive Models Model Deployment
  1. Predictions can change the outcome, leading to performative prediction. This can impact model performance.
  2. Performative prediction is common but often overlooked, affecting tasks like rent prediction and churn modeling.
  3. To deal with performative prediction, consider achieving performative stability, retraining models frequently, and reframing tasks as reinforcement learning.

Why you (probably) shouldn't use LIME to explain model predictions

159 implied HN points • 28 Mar 23
🕹 Technology Machine Learning Interpretability
  1. Local Interpretable Model-Agnostic Explanations (LIME) can be challenging to use effectively due to the difficulty in defining the 'local' neighborhood.
  2. The choice of kernel width in LIME is critical for the accuracy of the explanations, but it can be unclear how to select the appropriate width for different datasets and applications.
  3. There are alternative methods like Shapley values, counterfactual explanations, and what-if analysis that offer interpretability without the need to specify a neighborhood, making them potentially more suitable than LIME for certain cases.

Log Odds or Probability

139 implied HN points • 25 Apr 23
🔬 Science Statistics Interpretation Regression Probability
  1. Log odds are additive, probabilities are multiplicative. Some interpretation methods like expressing predictions as a linear sum may benefit from log odds.
  2. Edge transitions, like from 0.001 to 0.01, may sometimes be more significant than middle transitions, like 0.5 to 0.6.
  3. Probabilities offer intuitive understanding for decision-making, cost calculations, and are more commonly familiar compared to log odds.

When in Doubt, Abstain: Why Machine Learning Models Need to Know Their Limits

139 implied HN points • 18 Apr 23
🕹 Technology Machine Learning Data Ethics Artificial Intelligence Model Training
  1. Machine learning models should not always provide an answer and should learn to abstain if uncertain or lacking information.
  2. Abstaining from making predictions can help in various scenarios like uncertain decisions, out-of-distribution data, and biased outputs.
  3. Implementing methods like outlier detection, input checks, reinforcement learning, and measuring prediction uncertainty can help models in learning when to abstain.

Conformal Prediction is Available in Print 🥳

159 implied HN points • 07 Mar 23
🕹 Technology Machine Learning Books Uncertainty Python Statistics
  1. Conformal prediction quantifies uncertainty in machine learning models by producing prediction sets or intervals.
  2. Conformal prediction offers a way to get reliable uncertainty quantification by calibrating the uncertainty score of ML models.
  3. The book 'Introduction to Conformal Prediction With Python' serves as a practical and easy-to-understand resource to learn about this uncertainty quantification method.

Roles of Supervised Machine Learning in Science

179 implied HN points • 31 Jan 23
🔬 Science Machine Learning Research Tools Intervention
  1. Machine learning models play multiple roles in science: as study objects, scientific tools, and scientific models.
  2. Using machine learning models as study objects is common in science, focusing on predictive model performance comparisons.
  3. Machine learning models can be utilized as scientific tools and as scientific models, where they play a central role in understanding phenomena.

Understanding Different Uncertainty Mindsets

179 implied HN points • 24 Jan 23
🔬 Science Probability Modeling Uncertainty Machine Learning Statistics
  1. Understanding the fundamental difference between Bayesian and frequentist interpretations of probability is crucial for grasping uncertainty quantification techniques.
  2. Conformal prediction offers prediction regions with a frequentist interpretation, similar to confidence intervals in linear regression models.
  3. Conformal prediction shares similarities with the evaluation requirements and mindset of supervised machine learning, emphasizing the importance of separate calibration and ground truth data.

Quantify The Uncertainty Of Predictive Models With Conformal Prediction

239 implied HN points • 11 Oct 22
🕹 Technology Machine Learning Calibration Open Source Tools
  1. Machine learning models often lack the ability to express uncertainty, leading to overconfidence and potential inaccuracies in predictions.
  2. Conformal prediction is a useful method to quantify uncertainty in predictive models, offering benefits like speed, model-agnosticism, and statistical guarantees.
  3. To implement conformal prediction, one must have a heuristic score of uncertainty, ensuring that the calibration of uncertainty levels is reliable for more accurate predictions.

Same Model, Different Uses

219 implied HN points • 25 Oct 22
🕹 Technology Machine Learning Statistics
  1. The mindset of the modeler significantly influences the use and interpretation of models.
  2. There are various modeling mindsets such as frequentist inference, Bayesian inference, causal inference, and supervised machine learning, all of which can lead to the same final model.
  3. Different tasks require different modeling mindsets, and being well-versed in multiple mindsets can be beneficial for a data scientist.

The Way Of Model-Agnostic Machine Learning

139 implied HN points • 21 Feb 23
🕹 Technology Machine Learning Interpretation API
  1. Choosing the best model based on performance is crucial in machine learning, even if personal preferences may influence model selection.
  2. Embracing model-agnostic machine learning involves using software that enables flexible model choices, maintaining consistent APIs across models, and prioritizing model-agnostic interpretation methods.
  3. Real-world constraints and preferences often lead to model-specific approaches, but advancements in interpretation methods, uncertainty quantification, and technology are making model-agnostic modeling more feasible.

Week #4: Overview Of Conformal Predictors

139 implied HN points • 10 Jan 23
🕹 Technology Machine Learning Data science Research Methods Applications
  1. Conformal prediction is a versatile approach applicable to various machine learning tasks beyond just regression and classification.
  2. When learning about a new conformal prediction method, it's important to consider the machine learning task, non-conformity score used, and how the method deviates from the standard recipe.
  3. Staying up to date with new research in conformal prediction can be facilitated by resources like the 'Awesome Conformal Prediction' repository and following experts in the field on platforms like Twitter.

Unlock Causal Inference: 3 Obstacles, 8 Insights & 1 Resource

159 implied HN points • 29 Nov 22
🔬 Science Causal Inference Statistics Models Education Resources
  1. Causal inference can be challenging to start due to various obstacles like diverse approaches and neglected education on the topic.
  2. Understanding causal inference involves adjusting your modeling mindset to view it as a unique approach rather than just adding a new model.
  3. Key insights for causal inference include the importance of directed acyclic graphs, starting from a causal model, and the challenges of estimating causal effects from observational data.

Interpret Complex Pipelines By Drawing A Box

159 implied HN points • 22 Nov 22
🕹 Technology Data Analysis Interpretability
  1. Interpretation of complex pipelines can be challenging when model changes impact interpretability. Use model-agnostic interpretation methods to interpret arbitrary pipelines.
  2. Think of predictive models as pipelines with various steps like transformations and model ensembles. View the entire pipeline as the model for better interpretation.
  3. Draw the box around the entire pipeline in model-agnostic interpretation to gain insights into feature importance, prediction changes, and explanations, disregarding the specific models within the pipeline.

Improve Post-Hoc Interpretation By Leveraging Background Data

99 implied HN points • 21 Mar 23
🔬 Science Data interpretation
  1. Utilize background data creatively in analysis by considering it as more than just a nuisance for estimation
  2. Leverage background data to explore different scenarios like distribution shifts, feature effects in various data groups, and stability of model predictions
  3. Background data plays a crucial role in model-agnostic interpretation methods like Shapley values and permutation feature importance, providing opportunities to enhance analysis by smart selection

8 Pitfalls To Avoid When Interpreting Machine Learning Models

159 implied HN points • 18 Oct 22
🕹 Technology Machine Learning Uncertainty
  1. Different interpretation methods have different goals, so define your interpretation goal first and then choose the appropriate method.
  2. Ensure your model generalizes well by using proper out-of-sample evaluation like cross-validation.
  3. Consider using simpler models for better interpretability and always analyze and correct for dependencies and uncertainties in your interpretation.