We introduce MODEL SELECTOR, a framework for label-efficient selection of pretrained classifiers. Given a pool of unlabeled target data, MODEL SELECTOR samples a small subset of highly informative examples for labeling, in order to efficiently identify the best pretrained model for deployment on this target dataset. Through extensive experiments, we demonstrate that MODEL SELECTOR drastically reduces the need for labeled data while consistently picking the best or near-best performing model. Across 18 model collections on 16 different datasets, comprising over 1,500 pretrained models, MODEL SELECTOR reduces the labeling cost by up to 94.15% to identify the best model compared to the cost of the strongest baseline. Our results further highlight the robustness of MODEL SELECTOR in model selection, as it reduces the labeling cost by up to 72.41% when selecting a near-best model, whose accuracy is only within 1% of the best model.

Conformal prediction has shown spurring performance in constructing statistically rigorous prediction sets for arbitrary black-box machine learning models, assuming the data is exchangeable. However, even small adversarial perturbations during the inference can violate the exchangeability assumption, challenge the coverage guarantees, and result in a subsequent decline in empirical coverage. In this work, we propose a certifiably robust learning-reasoning conformal prediction framework (COLEP) via probabilistic circuits, which comprise a data-driven learning component that trains statistical models to learn different semantic concepts, and a reasoning component that encodes knowledge and characterizes the relationships among the trained models for logic reasoning. To achieve exact and efficient reasoning, we employ probabilistic circuits (PCs) within the reasoning component. Theoretically, we provide end-to-end certification of prediction coverage for COLEP in the presence of bounded adversarial perturbations. We also provide certified coverage considering the finite size of the calibration set. Furthermore, we prove that COLEP achieves higher prediction coverage and accuracy over a single model as long as the utilities of knowledge models are non-trivial. Empirically, we show the validity and tightness of our certified coverage, demonstrating the robust conformal prediction of COLEP on various datasets, including GTSRB, CIFAR10, and AwA2. We show that COLEP achieves up to 12% improvement in certified coverage on GTSRB, 9% on CIFAR-10, and 14% on AwA2.

Despite the impressive capabilities of large language models (LLMs) across diverse applications, they still suffer from trustworthiness issues, such as hallucinations and misalignments. Retrieval-augmented language models (RAG) have been proposed to enhance the credibility of generations by grounding external knowledge, but the theoretical understandings of their generation risks remains unexplored. In this paper, we answer: 1) whether RAG can indeed lead to low generation risks, 2) how to provide provable guarantees on the generation risks of RAG and vanilla LLMs, and 3) what sufficient conditions enable RAG models to reduce generation risks. We propose C-RAG, the first framework to certify generation risks for RAG models. Specifically, we provide conformal risk analysis for RAG models and certify an upper confidence bound of generation risks, which we refer to as conformal generation risk. We also provide theoretical guarantees on conformal generation risks for general bounded risk functions under test distribution shifts. We prove that RAG achieves a lower conformal generation risk than that of a single LLM when the quality of the retrieval model and transformer is non-trivial. Our intensive empirical results demonstrate the soundness and tightness of our conformal generation risk guarantees across four widely-used NLP datasets on four state-of-the-art retrieval models.

Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure development for the creation of next-generation public datasets that will advance machine learning science. We chart a path forward as a collective effort to sustain the creation and maintenance of these datasets and methods towards positive scientific, societal and business impact.

Methods for carefully selecting or generating a small set of training data to learn from, i.e., data pruning, coreset selection, and data distillation, have been shown to be effective in reducing the ever-increasing cost of training neural networks. Behind this success are rigorously designed strategies for identifying informative training examples out of large datasets. However, these strategies come with additional computational costs associated with subset selection or data distillation before training begins, and furthermore, many are shown to even under-perform random sampling in high data compression regimes. As such, many data pruning, coreset selection, or distillation methods may not reduce 'time-to-accuracy', which has become a critical efficiency measure of training deep neural networks over large datasets. In this work, we revisit a powerful yet overlooked random sampling strategy to address these challenges and introduce an approach called Repeated Sampling of Random Subsets (RSRS or RS2), where we randomly sample the subset of training data for each epoch of model training. We test RS2 against thirty state-of-the-art data pruning and data distillation methods across four datasets including ImageNet. Our results demonstrate that RS2 significantly reduces time-to-accuracy compared to existing techniques. For example, when training on ImageNet in the high-compression regime (using less than 10% of the dataset each epoch), RS2 yields accuracy improvements up to 29% compared to competing pruning methods while offering a runtime reduction of 7x. Beyond the above meta-study, we provide a convergence analysis for RS2 and discuss its generalization capability. The primary goal of our work is to establish RS2 as a competitive baseline for future data selection or distillation techniques aimed at efficient training.

Model selection from a set of pre-trained models is an emerging problem in machine learning and has implications in several practical scenarios. Industrial examples include cases in which a telecommunication company or a flight booking company have multiple ML models trained over different sliding windows of data and hope to pick the one that performs the best on a given day. For many real-world problems, unlabeled data is abundant and can be inexpensively collected, while labels are expensive to acquire and require human expertise. Consequently, there is a need to robustly identify the best model under limited labeling resources. Similarly, one often needs reasonable predictions for the unlabeled data while keeping the labeling budget low. Depending on data availability, one can consider two settings: the pool-based setting assumes that the learner has access to a pool of unlabeled data, and she tries to select informative data samples from the pool to achieve her task. The online (streaming) setting works with a stream of data, where the data arrives one at a time, and the learner decides to ask for the label of the data samples on the go or to just throw the sample away. While offering less options on which data to label next, this streaming setting alleviates the scalability challenge of storing and processing a large pool of examples in the pool-based setting. Another important aspect is the nature of the data: the instance/label pairs might be sampled i.i.d.

To automate the generation of interactive features, recent methods are proposed to either explicitly traverse the interactive feature space or implicitly express the interactions via intermediate activations of some designed models. These two kinds of methods show that there is essentially a trade-off between feature interpretability and efficient search. To possess both of their merits, we propose a novel method named Feature Interaction Via Edge Search (FIVES), which formulates the task of interactive feature generation as searching for edges on the defined feature graph. We first present our theoretical evidence that motivates us to search for interactive features in an inductive manner. Then we instantiate this search strategy by alternatively updating the edge structure and the predictive model of a graph neural network (GNN) associated with the defined feature graph. In this way, the proposed FIVES method traverses a trimmed search space and enables explicit feature generation according to the learned adjacency tensor of the GNN. Experimental results on both benchmark and real-world datasets demonstrate the advantages of FIVES over several state-of-the-art methods.

Machine learning (ML) applications have been thriving recently, largely attributed to the increasing availability of data. However, inconsistency and incomplete information are ubiquitous in real-world datasets, and their impact on ML applications remains elusive. In this paper, we present a formal study of this impact by extending the notion of Certain Answers for Codd tables, which has been explored by the database research community for decades, into the field of machine learning. Specifically, we focus on classification problems and propose the notion of "Certain Predictions" (CP) -- a test data example can be certainly predicted (CP'ed) if all possible classifiers trained on top of all possible worlds induced by the incompleteness of data would yield the same prediction. We study two fundamental CP queries: (Q1) checking query that determines whether a data example can be CP'ed; and (Q2) counting query that computes the number of classifiers that support a particular prediction (i.e., label). Given that general solutions to CP queries are, not surprisingly, hard without assumption over the type of classifier, we further present a case study in the context of nearest neighbor (NN) classifiers, where efficient solutions to CP queries can be developed -- we show that it is possible to answer both queries in linear or polynomial time over exponentially many possible worlds. We demonstrate one example use case of CP in the important application of "data cleaning for machine learning (DC for ML)." We show that our proposed CPClean approach built based on CP can often significantly outperform existing techniques in terms of classification accuracy with mild manual cleaning effort.

Modern scientific instruments produce vast amounts of data, which can overwhelm the processing ability of computer systems. Lossy compression of data is an intriguing solution but comes with its own dangers, such as potential signal loss, and the need for careful parameter optimization. In this work, we focus on a setting where this problem is especially acute compressive sensing frameworks for radio astronomy and ask: Can the precision of the data representation be lowered for all input data, with recovery guarantees and good practical performance? Our first contribution is a theoretical analysis of the Iterative Hard Thresholding (IHT) algorithm when all input data, that is, the measurement matrix and the observation, are quantized aggressively, to as little as 2 bits per value. Under reasonable constraints, we show that there exists a variant of low precision IHT which can still provide recovery guarantees. The second contribution is a tailored analysis of our general quantized framework to radio astronomy, showing that its conditions are satisfied in this case. We evaluate our approach using an FPGA implementation, and show that it can achieve up to 9.19x speed up with negligible loss of recovery quality, on real telescope data