Jeffrey A. Bilmes

Jacob Schreiber, Jeffrey Bilmes, William Stafford Noble

We present apricot, an open source Python package for selecting representative subsets from large data sets using submodular optimization. The package implements an efficient greedy selection algorithm that offers strong theoretical guarantees on the quality of the selected set. Two submodular set functions are implemented in apricot: facility location, which is broadly applicable but requires memory quadratic in the number of examples in the data set, and a feature-based function that is less broadly applicable but can scale to millions of examples. Apricot is extremely efficient, using both algorithmic speedups such as the lazy greedy algorithm and code optimizers such as numba. We demonstrate the use of subset selection by training machine learning models to comparable accuracy using either the full data set or a representative subset thereof. This paper presents an explanation of submodular selection, an overview of the features in apricot, and an application to several data sets. The code and tutorial Jupyter notebooks are available at https://github.com/jmschrei/apricot

Gantavya Bhatt, Yifang Chen, Arnav M. Das et al. · uw

Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to produce high quality responses for instructions are becoming prohibitively expensive, especially as the number of tasks spanned by instruction datasets continues to increase. Active learning is effective in identifying useful subsets of samples to annotate from an unlabeled pool, but its high computational cost remains a barrier to its widespread applicability in the context of LLMs. To mitigate the annotation cost of SFT and circumvent the computational bottlenecks of active learning, we propose using experimental design. Experimental design techniques select the most informative samples to label, and typically maximize some notion of uncertainty and/or diversity. In our work, we implement a framework that evaluates several existing and novel experimental design techniques and find that these methods consistently yield significant gains in label efficiency with little computational overhead. On generative tasks, our methods achieve the same generalization performance with only $50\%$ of annotation cost required by random sampling.

Rishabh Iyer, Jeff Bilmes

We are motivated by large scale submodular optimization problems, where standard algorithms that treat the submodular functions in the \emph{value oracle model} do not scale. In this paper, we present a model called the \emph{precomputational complexity model}, along with a unifying memoization based framework, which looks at the specific form of the given submodular function. A key ingredient in this framework is the notion of a \emph{precomputed statistic}, which is maintained in the course of the algorithms. We show that we can easily integrate this idea into a large class of submodular optimization problems including constrained and unconstrained submodular maximization, minimization, difference of submodular optimization, optimization with submodular constraints and several other related optimization problems. Moreover, memoization can be integrated in both discrete and continuous relaxation flavors of algorithms for these problems. We demonstrate this idea for several commonly occurring submodular functions, and show how the precomputational model provides significant speedups compared to the value oracle model. Finally, we empirically demonstrate this for large scale machine learning problems of data subset selection and summarization.

Rishabh Iyer, Jeff Bilmes

In this paper, we investigate a class of submodular problems which in general are very hard. These include minimizing a submodular cost function under combinatorial constraints, which include cuts, matchings, paths, etc., optimizing a submodular function under submodular cover and submodular knapsack constraints, and minimizing a ratio of submodular functions. All these problems appear in several real world problems but have hardness factors of $Ω(\sqrt{n})$ for general submodular cost functions. We show how we can achieve constant approximation factors when we restrict the cost functions to low rank sums of concave over modular functions. A wide variety of machine learning applications are very naturally modeled via this subclass of submodular functions. Our work therefore provides a tighter connection between theory and practice by enabling theoretically satisfying guarantees for a rich class of expressible, natural, and useful submodular cost models. We empirically demonstrate the utility of our models on real world problems of cooperative image matching and sensor placement with cooperative costs.

Jeffrey Bilmes, Wenruo Bai

We start with an overview of a class of submodular functions called SCMMs (sums of concave composed with non-negative modular functions plus a final arbitrary modular). We then define a new class of submodular functions we call {\em deep submodular functions} or DSFs. We show that DSFs are a flexible parametric family of submodular functions that share many of the properties and advantages of deep neural networks (DNNs). DSFs can be motivated by considering a hierarchy of descriptive concepts over ground elements and where one wishes to allow submodular interaction throughout this hierarchy. Results in this paper show that DSFs constitute a strictly larger class of submodular functions than SCMMs. We show that, for any integer $k>0$, there are $k$-layer DSFs that cannot be represented by a $k'$-layer DSF for any $k'<k$. This implies that, like DNNs, there is a utility to depth, but unlike DNNs, the family of DSFs strictly increase with depth. Despite this, we show (using a "backpropagation" like method) that DSFs, even with arbitrarily large $k$, do not comprise all submodular functions. In offering the above results, we also define the notion of an antitone superdifferential of a concave function and show how this relates to submodular functions (in general), DSFs (in particular), negative second-order partial derivatives, continuous submodularity, and concave extensions. To further motivate our analysis, we provide various special case results from matroid theory, comparing DSFs with forms of matroid rank, in particular the laminar matroid. Lastly, we discuss strategies to learn DSFs, and define the classes of deep supermodular functions, deep difference of submodular functions, and deep multivariate submodular functions, and discuss where these can be useful in applications.

Sunil Thulasidasan, Jeffrey Bilmes

We describe a graph-based semi-supervised learning framework in the context of deep neural networks that uses a graph-based entropic regularizer to favor smooth solutions over a graph induced by the data. The main contribution of this work is a computationally efficient, stochastic graph-regularization technique that uses mini-batches that are consistent with the graph structure, but also provides enough stochasticity (in terms of mini-batch data diversity) for convergence of stochastic gradient descent methods to good solutions. For this work, we focus on results of frame-level phone classification accuracy on the TIMIT speech corpus but our method is general and scalable to much larger data sets. Results indicate that our method significantly improves classification accuracy compared to the fully-supervised case when the fraction of labeled data is low, and it is competitive with other methods in the fully labeled case.

Sunil Thulasidasan, Jeffrey Bilmes, Garrett Kenyon

We describe a computationally efficient, stochastic graph-regularization technique that can be utilized for the semi-supervised training of deep neural networks in a parallel or distributed setting. We utilize a technique, first described in [13] for the construction of mini-batches for stochastic gradient descent (SGD) based on synthesized partitions of an affinity graph that are consistent with the graph structure, but also preserve enough stochasticity for convergence of SGD to good local minima. We show how our technique allows a graph-based semi-supervised loss function to be decomposed into a sum over objectives, facilitating data parallelism for scalable training of machine learning models. Empirical results indicate that our method significantly improves classification accuracy compared to the fully-supervised case when the fraction of labeled data is low, and in the parallel case, achieves significant speed-up in terms of wall-clock time to convergence. We show the results for both sequential and distributed-memory semi-supervised DNN training on a speech corpus.