Ali Malik

Guy Blanc, Jane Lange, Ali Malik et al.

Using the framework of boosting, we prove that all impurity-based decision tree learning algorithms, including the classic ID3, C4.5, and CART, are highly noise tolerant. Our guarantees hold under the strongest noise model of nasty noise, and we provide near-matching upper and lower bounds on the allowable noise rate. We further show that these algorithms, which are simple and have long been central to everyday machine learning, enjoy provable guarantees in the noisy setting that are unmatched by existing algorithms in the theoretical literature on decision tree learning. Taken together, our results add to an ongoing line of research that seeks to place the empirical success of these practical decision tree algorithms on firm theoretical footing.

Guy Blanc, Jane Lange, Ali Malik et al.

We show how any PAC learning algorithm that works under the uniform distribution can be transformed, in a blackbox fashion, into one that works under an arbitrary and unknown distribution $\mathcal{D}$. The efficiency of our transformation scales with the inherent complexity of $\mathcal{D}$, running in $\mathrm{poly}(n, (md)^d)$ time for distributions over $\{\pm 1\}^n$ whose pmfs are computed by depth-$d$ decision trees, where $m$ is the sample complexity of the original algorithm. For monotone distributions our transformation uses only samples from $\mathcal{D}$, and for general ones it uses subcube conditioning samples. A key technical ingredient is an algorithm which, given the aforementioned access to $\mathcal{D}$, produces an optimal decision tree decomposition of $\mathcal{D}$: an approximation of $\mathcal{D}$ as a mixture of uniform distributions over disjoint subcubes. With this decomposition in hand, we run the uniform-distribution learner on each subcube and combine the hypotheses using the decision tree. This algorithmic decomposition lemma also yields new algorithms for learning decision tree distributions with runtimes that exponentially improve on the prior state of the art -- results of independent interest in distribution learning.

Ali Malik, Stephen Mayhew, Chris Piech et al.

We study the problem of controlling the difficulty level of text generated by Large Language Models (LLMs) for contexts where end-users are not fully proficient, such as language learners. Using a novel framework, we evaluate the effectiveness of several key approaches for this task, including few-shot prompting, supervised finetuning, and reinforcement learning (RL), utilising both GPT-4 and open source alternatives like LLama2-7B and Mistral-7B. Our findings reveal a large performance gap between GPT-4 and the open source models when using prompt-based strategies. However, we show how to bridge this gap with a careful combination of finetuning and RL alignment. Our best model, CALM (CEFR-Aligned Language Model), surpasses the performance of GPT-4 and other strategies, at only a fraction of the cost. We further validate the quality of our results through a small-scale human study.

Allen Nie, Yash Chandak, Miroslav Suzara et al.

Large language models (LLMs) are quickly being adopted in a wide range of learning experiences, especially via ubiquitous and broadly accessible chat interfaces like ChatGPT and Copilot. This type of interface is readily available to students and teachers around the world, yet relatively little research has been done to assess the impact of such generic tools on student learning. Coding education is an interesting test case, both because LLMs have strong performance on coding tasks, and because LLM-powered support tools are rapidly becoming part of the workflow of professional software engineers. To help understand the impact of generic LLM use on coding education, we conducted a large-scale randomized control trial with 5,831 students from 146 countries in an online coding class in which we provided some students with access to a chat interface with GPT-4. We estimate positive benefits on exam performance for adopters, the students who used the tool, but over all students, the advertisement of GPT-4 led to a significant average decrease in exam participation. We observe similar decreases in other forms of course engagement. However, this decrease is modulated by the student's country of origin. Offering access to LLMs to students from low human development index countries increased their exam participation rate on average. Our results suggest there may be promising benefits to using LLMs in an introductory coding class, but also potential harms for engagement, which makes their longer term impact on student success unclear. Our work highlights the need for additional investigations to help understand the potential impact of future adoption and integration of LLMs into classrooms.

Guy Blanc, Jane Lange, Ali Malik et al.

We study a fundamental question concerning adversarial noise models in statistical problems where the algorithm receives i.i.d. draws from a distribution $\mathcal{D}$. The definitions of these adversaries specify the type of allowable corruptions (noise model) as well as when these corruptions can be made (adaptivity); the latter differentiates between oblivious adversaries that can only corrupt the distribution $\mathcal{D}$ and adaptive adversaries that can have their corruptions depend on the specific sample $S$ that is drawn from $\mathcal{D}$. In this work, we investigate whether oblivious adversaries are effectively equivalent to adaptive adversaries, across all noise models studied in the literature. Specifically, can the behavior of an algorithm $\mathcal{A}$ in the presence of oblivious adversaries always be well-approximated by that of an algorithm $\mathcal{A}'$ in the presence of adaptive adversaries? Our first result shows that this is indeed the case for the broad class of statistical query algorithms, under all reasonable noise models. We then show that in the specific case of additive noise, this equivalence holds for all algorithms. Finally, we map out an approach towards proving this statement in its fullest generality, for all algorithms and under all reasonable noise models.

Rishi Bommasani, Drew A. Hudson, Ehsan Adeli et al.

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.

Ali Malik, Volodymyr Kuleshov, Jiaming Song et al.

Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning. However, predictive uncertainties---especially ones derived from modern deep learning systems---can be inaccurate and impose a bottleneck on performance. This paper explores which uncertainties are needed for model-based reinforcement learning and argues that good uncertainties must be calibrated, i.e. their probabilities should match empirical frequencies of predicted events. We describe a simple way to augment any model-based reinforcement learning agent with a calibrated model and show that doing so consistently improves planning, sample complexity, and exploration. On the \textsc{HalfCheetah} MuJoCo task, our system achieves state-of-the-art performance using 50\% fewer samples than the current leading approach. Our findings suggest that calibration can improve the performance of model-based reinforcement learning with minimal computational and implementation overhead.

Chris Piech, Ali Malik, Laura M Scott et al.

Chart-based visual acuity measurements are used by billions of people to diagnose and guide treatment of vision impairment. However, the ubiquitous eye exam has no mechanism for reasoning about uncertainty and as such, suffers from a well-documented reproducibility problem. In this paper we make two core contributions. First, we uncover a new parametric probabilistic model of visual acuity response based on detailed measurements of patients with eye disease. Then, we present an adaptive, digital eye exam using modern artificial intelligence techniques which substantially reduces acuity exam error over existing approaches, while also introducing the novel ability to model its own uncertainty and incorporate prior beliefs. Using standard evaluation metrics, we estimate a 74% reduction in prediction error compared to the ubiquitous chart-based eye exam and up to 67% reduction compared to the previous best digital exam. For patients with eye disease, the novel ability to finely measure acuity from home could be a crucial part in early diagnosis. We provide a web implementation of our algorithm for anyone in the world to use. The insights in this paper also provide interesting implications for the field of psychometric Item Response Theory.

Nate Gruver, Ali Malik, Brahm Capoor et al.

Understanding large-scale patterns in student course enrollment is a problem of great interest to university administrators and educational researchers. Yet important decisions are often made without a good quantitative framework of the process underlying student choices. We propose a probabilistic approach to modelling course enrollment decisions, drawing inspiration from multilabel classification and mixture models. We use ten years of anonymized student transcripts from a large university to construct a Gaussian latent variable model that learns the joint distribution over course enrollments. The models allow for a diverse set of inference queries and robustness to data sparsity. We demonstrate the efficacy of this approach in comparison to others, including deep learning architectures, and demonstrate its ability to infer the underlying student interests that guide enrollment decisions.

Ali Malik, Mike Wu, Vrinda Vasavada et al.

Access to high-quality education at scale is limited by the difficulty of providing student feedback on open-ended assignments in structured domains like computer programming, graphics, and short response questions. This problem has proven to be exceptionally difficult: for humans, it requires large amounts of manual work, and for computers, until recently, achieving anything near human-level accuracy has been unattainable. In this paper, we present generative grading: a novel computational approach for providing feedback at scale that is capable of accurately grading student work and providing nuanced, interpretable feedback. Our approach uses generative descriptions of student cognition, written as probabilistic programs, to synthesise millions of labelled example solutions to a problem; we then learn to infer feedback for real student solutions based on this cognitive model. We apply our methods to three settings. In block-based coding, we achieve a 50% improvement upon the previous best results for feedback, achieving super-human accuracy. In two other widely different domains -- graphical tasks and short text answers -- we achieve major improvement over the previous state of the art by about 4x and 1.5x respectively, approaching human accuracy. In a real classroom, we ran an experiment where we used our system to augment human graders, yielding doubled grading accuracy while halving grading time.