Despite the rich existing literature about minimax optimization in continuous settings, only very partial results of this kind have been obtained for combinatorial settings. In this paper, we fill this gap by providing a characterization of submodular minimax optimization, the problem of finding a set (for either the min or the max player) that is effective against every possible response. We show when and under what conditions we can find such sets. We also demonstrate how minimax submodular optimization provides robust solutions for downstream machine learning applications such as (i) prompt engineering in large language models, (ii) identifying robust waiting locations for ride-sharing, (iii) kernelization of the difficulty of instances of the last setting, and (iv) finding adversarial images. Our experiments show that our proposed algorithms consistently outperform other baselines.

In-Context Learning (ICL) is the ability of Large Language Models (LLMs) to perform new tasks when conditioned on prompts comprising a few task examples. However, ICL performance can be critically sensitive to the choice of examples. To dynamically select the best examples for every test input, we propose Example Gisting, a novel approach for training example encoders through supervised finetuning with an attention bottleneck between the inputs and outputs. These gist models form the basis for GistScore, a novel metric for scoring and selecting informative examples. Further, we experiment with two variations: (1) finetuning gist models for each dataset and (2) multi-task training a single model on a large collection of datasets. The latter can be used for new tasks out-of-the-box, enabling a training-free ICL pipeline. Evaluations with 21 datasets spanning 9 tasks and 8 diverse LLMs show that our fine-tuned models get state-of-the-art ICL performance with over 20% absolute gain over off-the-shelf retrievers and 5% over the best prior methods. Further, our multi-task model generalizes well to new tasks, datasets, and prompt templates. Selection using this model matches or outperforms prior methods while being three orders of magnitude faster than the strongest training-free baseline.

A common training technique for language models is teacher forcing (TF). TF attempts to match human language exactly, even though identical meanings can be expressed in different ways. This motivates use of sequence-level objectives for dialogue response generation. In this paper, we study the efficacy of various offline reinforcement learning (RL) methods to maximize such objectives. We present a comprehensive evaluation across multiple datasets, models, and metrics. Offline RL shows a clear performance improvement over teacher forcing while not inducing training instability or sacrificing practical training budgets.

Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled. This paper introduces a new method to identify such samples and mitigate their impact when training neural networks. At the heart of our algorithm is the Area Under the Margin (AUM) statistic, which exploits differences in the training dynamics of clean and mislabeled samples. A simple procedure - adding an extra class populated with purposefully mislabeled threshold samples - learns a AUM upper bound that isolates mislabeled data. This approach consistently improves upon prior work on synthetic and real-world datasets. On the WebVision50 classification task our method removes 17% of training data, yielding a 1.6% (absolute) improvement in test error. On CIFAR100 removing 13% of the data leads to a 1.2% drop in error.

Greedy algorithms are widely used for problems in machine learning such as feature selection and set function optimization. Unfortunately, for large datasets, the running time of even greedy algorithms can be quite high. This is because for each greedy step we need to refit a model or calculate a function using the previously selected choices and the new candidate. Two algorithms that are faster approximations to the greedy forward selection were introduced recently [Mirzasoleiman et al., 2013, 2015]. They achieve better performance by exploiting stochastic evaluation and distributed computation respectively. Both algorithms have provable performance guarantees for submodular functions. In this paper we show that divergent from previously held opinion, submodularity is not required to obtain approximation guarantees for these two algorithms. Specifically, we show that a generalized concept of weak submodularity suffices to give multiplicative approximation guarantees. Our result extends the applicability of these algorithms to a larger class of functions. Furthermore, we show that a bounded submodularity ratio can be used to provide data dependent bounds that can sometimes be tighter also for submodular functions. We empirically validate our work by showing superior performance of fast greedy approximations versus several established baselines on artificial and real datasets.

We provide new approximation guarantees for greedy low rank matrix estimation under standard assumptions of restricted strong convexity and smoothness. Our novel analysis also uncovers previously unknown connections between the low rank estimation and combinatorial optimization, so much so that our bounds are reminiscent of corresponding approximation bounds in submodular maximization. Additionally, we provide also provide statistical recovery guarantees. Finally, we present empirical comparison of greedy estimation with established baselines on two important real-world problems.

In many machine learning applications, it is important to explain the predictions of a black-box classifier. For example, why does a deep neural network assign an image to a particular class? We cast interpretability of black-box classifiers as a combinatorial maximization problem and propose an efficient streaming algorithm to solve it subject to cardinality constraints. By extending ideas from Badanidiyuru et al. [2014], we provide a constant factor approximation guarantee for our algorithm in the case of random stream order and a weakly submodular objective function. This is the first such theoretical guarantee for this general class of functions, and we also show that no such algorithm exists for a worst case stream order. Our algorithm obtains similar explanations of Inception V3 predictions 10 times faster than the state-of-the-art LIME framework of Ribeiro et al. [2016].

We present a novel distributed algorithm for counting all four-node induced subgraphs in a big graph. These counts, called the 4-profile, describe a graph's connectivity properties and have found several uses ranging from bioinformatics to spam detection. We also study the more complicated problem of estimating the local 4-profiles centered at each vertex of the graph. The local 4-profile embeds every vertex in an 11-dimensional space that characterizes the local geometry of its neighborhood: vertices that connect different clusters will have different local 4-profiles compared to those that are only part of one dense cluster.

We study the problem of approximating the 3-profile of a large graph. 3-profiles are generalizations of triangle counts that specify the number of times a small graph appears as an induced subgraph of a large graph. Our algorithm uses the novel concept of 3-profile sparsifiers: sparse graphs that can be used to approximate the full 3-profile counts for a given large graph. Further, we study the problem of estimating local and ego 3-profiles, two graph quantities that characterize the local neighborhood of each vertex of a graph.

Index coding, initially introduced within theoretical computer science to address a specialized class of problems, has gained significant interest within communications and networking communities in recent years. Index coding has been shown to be analogous to a large class of challenging wired network coding and wireless multi-terminal problems, the latter class being of primary interest in this paper. Here, a (relaxed) rank minimization based analytic framework is presented for wireless index coding, which represents a first step in a systematic algorithmic approach to index coding for practical use. Further, the paper demonstrates its applicability over a real-world wireless testbed. The scheme operates at the network layer, and can be understood as a (non-trivial) generalization of existing principles of random linear network coding. Experimental results demonstrate that, for a class of network topologies, the rank-minimized index coding system presents a throughput gain of 50 to 100 percent greater than random linear coding for this system.