Causal reasoning is viewed as crucial for achieving human-level machine intelligence. Recent advances in language models have expanded the horizons of artificial intelligence across various domains, sparking inquiries into their potential for causal reasoning. In this work, we introduce Causal evaluation of Language Models (CaLM), which, to the best of our knowledge, is the first comprehensive benchmark for evaluating the causal reasoning capabilities of language models. First, we propose the CaLM framework, which establishes a foundational taxonomy consisting of four modules: causal target (i.e., what to evaluate), adaptation (i.e., how to obtain the results), metric (i.e., how to measure the results), and error (i.e., how to analyze the bad results). This taxonomy defines a broad evaluation design space while systematically selecting criteria and priorities. Second, we compose the CaLM dataset, comprising 126,334 data samples, to provide curated sets of causal targets, adaptations, metrics, and errors, offering extensive coverage for diverse research pursuits. Third, we conduct an extensive evaluation of 28 leading language models on a core set of 92 causal targets, 9 adaptations, 7 metrics, and 12 error types. Fourth, we perform detailed analyses of the evaluation results across various dimensions (e.g., adaptation, scale). Fifth, we present 50 high-level empirical findings across 9 dimensions (e.g., model), providing valuable guidance for future language model development. Finally, we develop a multifaceted platform, including a website, leaderboards, datasets, and toolkits, to support scalable and adaptable assessments. We envision CaLM as an ever-evolving benchmark for the community, systematically updated with new causal targets, adaptations, models, metrics, and error types to reflect ongoing research advancements. Project website is at https://opencausalab.github.io/CaLM.

In this work, we introduce a novel approach to regularization in multivariable regression problems. Our regularizer, called DLoss, penalises differences between the model's derivatives and derivatives of the data generating function as estimated from the training data. We call these estimated derivatives data derivatives. The goal of our method is to align the model to the data, not only in terms of target values but also in terms of the derivatives involved. To estimate data derivatives, we select (from the training data) 2-tuples of input-value pairs, using either nearest neighbour or random, selection. On synthetic and real datasets, we evaluate the effectiveness of adding DLoss, with different weights, to the standard mean squared error loss. The experimental results show that with DLoss (using nearest neighbour selection) we obtain, on average, the best rank with respect to MSE on validation data sets, compared to no regularization, L2 regularization, and Dropout.

The adoption of artificial intelligence (AI) across industries has led to the widespread use of complex black-box models and interpretation tools for decision making. This paper proposes an adversarial framework to uncover the vulnerability of permutation-based interpretation methods for machine learning tasks, with a particular focus on partial dependence (PD) plots. This adversarial framework modifies the original black box model to manipulate its predictions for instances in the extrapolation domain. As a result, it produces deceptive PD plots that can conceal discriminatory behaviors while preserving most of the original model's predictions. This framework can produce multiple fooled PD plots via a single model. By using real-world datasets including an auto insurance claims dataset and COMPAS (Correctional Offender Management Profiling for Alternative Sanctions) dataset, our results show that it is possible to intentionally hide the discriminatory behavior of a predictor and make the black-box model appear neutral through interpretation tools like PD plots while retaining almost all the predictions of the original black-box model. Managerial insights for regulators and practitioners are provided based on the findings.

It was first introduced to data analysis by Hoerl (1959) and later formulated in Hoerl and Kennard (1970b,a) for providing a robust solution to some of the persistent challenges encountered in traditional linear regression techniques; see Hoerl (1985) for a nice review. Emerging as a fundamental technique in predictive modeling, ridge regression addresses issues such as multicollinearity and overfitting, which commonly afflict predictive models dealing with high-dimensional data. Since its inception, ridge regression's practical adoption persists due to its superior performance over the least-squares estimator in various scenarios, evident in applications across neuroscience, chemistry, biology, and economics; see Leonard et al. (2023), Zahrt et al. (2019), Otwinowski and Plotkin (2014), Giannone et al. (2021), and Abadie and Kasy (2019), among others, underscoring its empirical effectiveness. From a shrinkage perspective, the ridge estimator also dominates the least-squares solutions in the sense that its mean-squared errors (MSEs) can be smaller, which provides a reasonable explanation on the empirical effectiveness of ridge estimators. See Theobald (1974), Athey and Imbens (2019), Hastie (2020), Hansen (2022a), and a comprehensive introduction to ridge regression in van Wieringen (2023). The ridge estimator offers a closed-form expression that simplifies both theoretical and empirical analyses. It aligns with the dense modeling techniques of Giannone et al. (2021), which acknowledge the potential significance of all explanatory variables for prediction. Empirical studies, such as those in Giannone et al. (2021), indicate that dense models generally tend to outperform the sparse ones in out-of-sample economic prediction performance. Similarly, Abadie and Kasy (2019) find that the ridge estimators dominate the lasso and the pre-testing estimators in terms of the risks when the effects of different predictors on the dependent variable are "smoothly distributed".

As a natural extension to the standard conformal prediction method, several conformal risk control methods have been recently developed and applied to various learning problems. In this work, we seek to control the conformal risk in expectation for ordinal classification tasks, which have broad applications to many real problems. For this purpose, we firstly formulated the ordinal classification task in the conformal risk control framework, and provided theoretic risk bounds of the risk control method. Then we proposed two types of loss functions specially designed for ordinal classification tasks, and developed corresponding algorithms to determine the prediction set for each case to control their risks at a desired level. We demonstrated the effectiveness of our proposed methods, and analyzed the difference between the two types of risks on three different datasets, including a simulated dataset, the UTKFace dataset and the diabetic retinopathy detection dataset.

Statistical learning theory and the Probably Approximately Correct (PAC) criterion are the common approach to mathematical learning theory. PAC is widely used to analyze learning problems and algorithms, and have been studied thoroughly. Uniform worst case bounds on the convergence rate have been well established using, e.g., VC theory or Radamacher complexity. However, in a typical scenario the performance could be much better. In this paper, we consider PAC learning using a somewhat different tradeoff, the error exponent - a well established analysis method in Information Theory - which describes the exponential behavior of the probability that the risk will exceed a certain threshold as function of the sample size. We focus on binary classification and find, under some stability assumptions, an improved distribution dependent error exponent for a wide range of problems, establishing the exponential behavior of the PAC error probability in agnostic learning. Interestingly, under these assumptions, agnostic learning may have the same error exponent as realizable learning. The error exponent criterion can be applied to analyze knowledge distillation, a problem that so far lacks a theoretical analysis.

The Bayes coding algorithm for context tree source is a successful example of Bayesian tree estimation in text compression in information theory. This algorithm provides an efficient parametric representation of the posterior tree distribution and exact updating of its parameters. We apply this algorithm to a clustering task in machine learning. More specifically, we apply it to Bayesian estimation of the tree-structured stick-breaking process (TS-SBP) mixture models. For TS-SBP mixture models, only Markov chain Monte Carlo methods have been proposed so far, but any variational Bayesian methods have not been proposed yet. In this paper, we propose a variational Bayesian method that has a subroutine similar to the Bayes coding algorithm for context tree sources. We confirm its behavior by a numerical experiment on a toy example.

Neural operators, serving as physics surrogate models, have recently gained increased interest. With ever increasing problem complexity, the natural question arises: what is an efficient way to scale neural operators to larger and more complex simulations - most importantly by taking into account different types of simulation datasets. This is of special interest since, akin to their numerical counterparts, different techniques are used across applications, even if the underlying dynamics of the systems are similar. Whereas the flexibility of transformers has enabled unified architectures across domains, neural operators mostly follow a problem specific design, where GNNs are commonly used for Lagrangian simulations and grid-based models predominate Eulerian simulations. We introduce Universal Physics Transformers (UPTs), an efficient and unified learning paradigm for a wide range of spatio-temporal problems. UPTs operate without grid- or particle-based latent structures, enabling flexibility and scalability across meshes and particles. UPTs efficiently propagate dynamics in the latent space, emphasized by inverse encoding and decoding techniques. Finally, UPTs allow for queries of the latent space representation at any point in space-time. We demonstrate diverse applicability and efficacy of UPTs in mesh-based fluid simulations, and steady-state Reynolds averaged Navier-Stokes simulations, and Lagrangian-based dynamics.

While many methods address these two issues separately, only a few currently deal with both simultaneously. In this paper, we introduce Utility-based Perturbed Gradient Descent (UPGD) as a novel approach for the continual learning of representations. UPGD combines gradient updates with perturbations, where it applies smaller modifications to more useful units, protecting them from forgetting, and larger modifications to less useful units, rejuvenating their plasticity. We use a challenging streaming learning setup where continual learning problems have hundreds of non-stationarities and unknown task boundaries. We show that many existing methods suffer from at least one of the issues, predominantly manifested by their decreasing accuracy over tasks. On the other hand, UPGD continues to improve performance and surpasses or is competitive with all methods in all problems. Finally, in extended reinforcement learning experiments with PPO, we show that while Adam exhibits a performance drop after initial learning, UPGD avoids it by addressing both continual learning issues. Continual learning remains a significant hurdle for artificial intelligence, despite advancements in natural language processing, games, and computer vision. Catastrophic forgetting (McCloskey & Cohen 1989, Hetherington & Seidenberg 1989) in neural networks is widely recognized as a major challenge of continual learning (De Lange et al. 2021). The phenomenon manifests as the failure of gradient-based methods like SGD or Adam to retain or leverage past knowledge due to forgetting or overwriting previously learned units (Kirkpatrick et al. 2017). This issue also raises a concern for reusing large practical models, where finetuning them for new tasks causes significant forgetting of pretrained models (Chen et al. 2020, He et al. 2021). Methods for mitigating catastrophic forgetting are primarily designed for specific settings. These include settings with independently and identically distributed (i.i.d.) samples, tasks fully contained within a batch or dataset, growing memory requirements, known task boundaries, storing past samples, and offline evaluation. Such setups are often impractical in situations where continual learning is paramount, such as on-device learning. For example, retaining samples may not be possible due to the limitation of computational resources (Hayes et al. 2019, Hayes et al. 2020, Hayes & Kannan 2022, Wang et al. 2023) or concerns over data privacy (Van de Ven et al. 2020). In the challenging and practical setting of streaming learning, catastrophic forgetting is more severe and remains largely unaddressed (Hayes et al. 2019). In streaming learning, samples are presented to the learner as they arise, which is non-i.i.d. in most practical problems.

Cultured meat has the potential to provide a complementary meat industry with reduced environmental, ethical, and health impacts. However, major technological challenges remain which require time- and resource-intensive research and development efforts. Machine learning has the potential to accelerate cultured meat technology by streamlining experiments, predicting optimal results, and reducing experimentation time and resources. However, the use of machine learning in cultured meat is in its infancy. This review covers the work available to date on the use of machine learning in cultured meat and explores future possibilities. We address four major areas of cultured meat research and development: establishing cell lines, cell culture media design, microscopy and image analysis, and bioprocessing and food processing optimization. This review aims to provide the foundation necessary for both cultured meat and machine learning scientists to identify research opportunities at the intersection between cultured meat and machine learning.