具有数百万参数的过度参数化模型取得了巨大成功。在这项工作中，我们问：至少由于学习者的\ emph {计算}限制，对大型模型的需求至少可以部分原因吗？此外，我们问，这种情况是否加剧了\ emph {robust}学习？我们证明确实可能是这种情况。我们展示了与信息理论学习者所需的学习任务相比，计算有限的学习者需要\ emph {明显更多的模型参数。此外，我们表明，对于健壮的学习可能需要更多的模型参数。特别是，对于计算有限的学习者，我们扩展了Bubeck and Sellke [Neurips'2021]的最新结果，该结果表明，强大的模型可能需要更多的参数，并表明有限学习者可能需要更多的参数数量。然后，我们解决以下相关的问题：我们是否希望通过限制\ emph {fersversaries}来纠正强大计算界限学习的情况，以便为了获得更少的参数获得模型而在计算上进行计算？再次，我们证明这是可能的。具体而言，在Garg，Jha，Mahloujifar和Mahmoody [Alt'2020]的基础上，我们演示了一项学习任务，可以有效，强大地对计算界限的攻击者进行有效，强大的学习，同时对信息理论攻击者需要强大学习者要使用更多参数。

中毒攻击已成为对机器学习算法的重要安全威胁。已经证明对培训集进行小变化的对手，例如添加特制的数据点，可以损害输出模型的性能。一些更强大的中毒攻击需要全面了解培训数据。这种叶子打开了使用没有完全了解干净训练集的中毒攻击来实现相同的攻击结果的可能性。在这项工作中，我们启动了对上述问题的理论研究。具体而言，对于具有套索的特征选择的情况，我们表明全信息对手（基于培训数据的其余部分的工艺中毒示例）可从未获得培训集的最佳攻击者提供了更强的最佳攻击者数据分发。我们的分离结果表明，数据感知和数据疏忽的两个设置从根本上不同，我们不能希望在这些场景中始终达到相同的攻击或辩护。

Learning policies from fixed offline datasets is a key challenge to scale up reinforcement learning (RL) algorithms towards practical applications. This is often because off-policy RL algorithms suffer from distributional shift, due to mismatch between dataset and the target policy, leading to high variance and over-estimation of value functions. In this work, we propose variance regularization for offline RL algorithms, using stationary distribution corrections. We show that by using Fenchel duality, we can avoid double sampling issues for computing the gradient of the variance regularizer. The proposed algorithm for offline variance regularization (OVAR) can be used to augment any existing offline policy optimization algorithms. We show that the regularizer leads to a lower bound to the offline policy optimization objective, which can help avoid over-estimation errors, and explains the benefits of our approach across a range of continuous control domains when compared to existing state-of-the-art algorithms.

In the process of materials discovery, chemists currently need to perform many laborious, time-consuming, and often dangerous lab experiments. To accelerate this process, we propose a framework for robots to assist chemists by performing lab experiments autonomously. The solution allows a general-purpose robot to perform diverse chemistry experiments and efficiently make use of available lab tools. Our system can load high-level descriptions of chemistry experiments, perceive a dynamic workspace, and autonomously plan the required actions and motions to perform the given chemistry experiments with common tools found in the existing lab environment. Our architecture uses a modified PDDLStream solver for integrated task and constrained motion planning, which generates plans and motions that are guaranteed to be safe by preventing collisions and spillage. We present a modular framework that can scale to many different experiments, actions, and lab tools. In this work, we demonstrate the utility of our framework on three pouring skills and two foundational chemical experiments for materials synthesis: solubility and recrystallization. More experiments and updated evaluations can be found at https://ac-rad.github.io/arc-icra2023.

This paper proposes an easy-to-compute upper bound for the overlap index between two probability distributions without requiring any knowledge of the distribution models. The computation of our bound is time-efficient and memory-efficient and only requires finite samples. The proposed bound shows its value in one-class classification and domain shift analysis. Specifically, in one-class classification, we build a novel one-class classifier by converting the bound into a confidence score function. Unlike most one-class classifiers, the training process is not needed for our classifier. Additionally, the experimental results show that our classifier \textcolor{\colorname}{can be accurate with} only a small number of in-class samples and outperforms many state-of-the-art methods on various datasets in different one-class classification scenarios. In domain shift analysis, we propose a theorem based on our bound. The theorem is useful in detecting the existence of domain shift and inferring data information. The detection and inference processes are both computation-efficient and memory-efficient. Our work shows significant promise toward broadening the applications of overlap-based metrics.

We propose a framework in which multiple entities collaborate to build a machine learning model while preserving privacy of their data. The approach utilizes feature embeddings from shared/per-entity feature extractors transforming data into a feature space for cooperation between entities. We propose two specific methods and compare them with a baseline method. In Shared Feature Extractor (SFE) Learning, the entities use a shared feature extractor to compute feature embeddings of samples. In Locally Trained Feature Extractor (LTFE) Learning, each entity uses a separate feature extractor and models are trained using concatenated features from all entities. As a baseline, in Cooperatively Trained Feature Extractor (CTFE) Learning, the entities train models by sharing raw data. Secure multi-party algorithms are utilized to train models without revealing data or features in plain text. We investigate the trade-offs among SFE, LTFE, and CTFE in regard to performance, privacy leakage (using an off-the-shelf membership inference attack), and computational cost. LTFE provides the most privacy, followed by SFE, and then CTFE. Computational cost is lowest for SFE and the relative speed of CTFE and LTFE depends on network architecture. CTFE and LTFE provide the best accuracy. We use MNIST, a synthetic dataset, and a credit card fraud detection dataset for evaluations.

Exploratory data analytics (EDA) is a sequential decision making process where analysts choose subsequent queries that might lead to some interesting insights based on the previous queries and corresponding results. Data processing systems often execute the queries on samples to produce results with low latency. Different downsampling strategy preserves different statistics of the data and have different magnitude of latency reductions. The optimum choice of sampling strategy often depends on the particular context of the analysis flow and the hidden intent of the analyst. In this paper, we are the first to consider the impact of sampling in interactive data exploration settings as they introduce approximation errors. We propose a Deep Reinforcement Learning (DRL) based framework which can optimize the sample selection in order to keep the analysis and insight generation flow intact. Evaluations with 3 real datasets show that our technique can preserve the original insight generation flow while improving the interaction latency, compared to baseline methods.

Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works like WiseFT (Wortsman et al., 2021) and LP-FT (Kumar et al., 2022) have shown that even subtle differences in the finetuning process can lead to surprisingly large differences in the final performance, both for in-distribution (ID) and out-of-distribution (OOD) data. In this work, we show that a natural and simple approach of mimicking contrastive pretraining consistently outperforms alternative finetuning approaches. Specifically, we cast downstream class labels as text prompts and continue optimizing the contrastive loss between image embeddings and class-descriptive prompt embeddings (contrastive finetuning). Our method consistently outperforms baselines across 7 distribution shifts, 6 transfer learning, and 3 few-shot learning benchmarks. On WILDS-iWILDCam, our proposed approach FLYP outperforms the top of the leaderboard by $2.3\%$ ID and $2.7\%$ OOD, giving the highest reported accuracy. Averaged across 7 OOD datasets (2 WILDS and 5 ImageNet associated shifts), FLYP gives gains of $4.2\%$ OOD over standard finetuning and outperforms the current state of the art (LP-FT) by more than $1\%$ both ID and OOD. Similarly, on 3 few-shot learning benchmarks, our approach gives gains up to $4.6\%$ over standard finetuning and $4.4\%$ over the state of the art. In total, these benchmarks establish contrastive finetuning as a simple, intuitive, and state-of-the-art approach for supervised finetuning of image-text models like CLIP. Code is available at https://github.com/locuslab/FLYP.

A number of competing hypotheses have been proposed to explain why small-batch Stochastic Gradient Descent (SGD)leads to improved generalization over the full-batch regime, with recent work crediting the implicit regularization of various quantities throughout training. However, to date, empirical evidence assessing the explanatory power of these hypotheses is lacking. In this paper, we conduct an extensive empirical evaluation, focusing on the ability of various theorized mechanisms to close the small-to-large batch generalization gap. Additionally, we characterize how the quantities that SGD has been claimed to (implicitly) regularize change over the course of training. By using micro-batches, i.e. disjoint smaller subsets of each mini-batch, we empirically show that explicitly penalizing the gradient norm or the Fisher Information Matrix trace, averaged over micro-batches, in the large-batch regime recovers small-batch SGD generalization, whereas Jacobian-based regularizations fail to do so. This generalization performance is shown to often be correlated with how well the regularized model's gradient norms resemble those of small-batch SGD. We additionally show that this behavior breaks down as the micro-batch size approaches the batch size. Finally, we note that in this line of inquiry, positive experimental findings on CIFAR10 are often reversed on other datasets like CIFAR100, highlighting the need to test hypotheses on a wider collection of datasets.

Change point detection (CPD) methods aim to detect abrupt changes in time-series data. Recent CPD methods have demonstrated their potential in identifying changes in underlying statistical distributions but often fail to capture complex changes in the correlation structure in time-series data. These methods also fail to generalize effectively, as even within the same time-series, different kinds of change points (CPs) may arise that are best characterized by different types of time-series perturbations. To address this issue, we propose TiVaCPD, a CPD methodology that uses a time-varying graphical lasso based method to identify changes in correlation patterns between features over time, and combines that with an aggregate Kernel Maximum Mean Discrepancy (MMD) test to identify subtle changes in the underlying statistical distributions of dynamically established time windows. We evaluate the performance of TiVaCPD in identifying and characterizing various types of CPs in time-series and show that our method outperforms current state-of-the-art CPD methods for all categories of CPs.