arXiv research

The paper introduces submodular information measures for machine learning applications.

In this paper, we present an algorithm for minimizing the difference between two submodular functions using a variational framework which is based on (an extension of) the concave-convex procedure [17]. Because several commonly used metrics in machine learning, like mutual information and conditional mutual information…

In the era of big data, learning from categorical features with very large vocabularies (e.g., 28 million for the Criteo click prediction dataset) has become a practical challenge for machine learning researchers and practitioners. We design a highly-scalable vocabulary compression algorithm that seeks to maximize the …

New method selects features via tensor decomposition and submodular optimization.

The paper tackles model selection for unseen tasks by capturing relationships among checkpoints.

We consider the problem of optimal budget allocation for crowdsourcing problems, allocating users to tasks to maximize our final confidence in the crowdsourced answers. Such an optimized worker assignment method allows us to boost the efficacy of any popular crowdsourcing estimation algorithm. We consider a mutual info…

Submodularity is one of the most well-studied properties of problem classes in combinatorial optimization and many applications of machine learning and data mining, with strong implications for guaranteed optimization. In this thesis, we investigate the role of submodularity in provable non-convex optimization and vali…

Study on maximizing submodular functions with limited updates, achieving tight bounds and poly-time algorithms.

The ability to integrate information in the brain is considered to be an essential property for cognition and consciousness. Integrated Information Theory (IIT) hypothesizes that the amount of integrated information ($Φ$) in the brain is related to the level of consciousness. IIT proposes that to quantify information i…

A new framework uses directed information to efficiently select context chunks.

Optimal subset selection for hypothesis testing with penalties.

In this paper, we propose three online algorithms for submodular maximisation. The first one, Mono-Frank-Wolfe, reduces the number of per-function gradient evaluations from $T^{1/2}$ [Chen2018Online] and $T^{3/2}$ [chen2018projection] to 1, and achieves a $(1-1/e)$-regret bound of $O(T^{4/5})$. The second one, Bandit-F…

In this paper, we consider the problem of black box continuous submodular maximization where we only have access to the function values and no information about the derivatives is provided. For a monotone and continuous DR-submodular function, and subject to a bounded convex body constraint, we propose Black-box Contin…

Paper proposes DG-ETC for online submodular maximization with stochastic bandit feedback.

This paper studies robust payoff allocation in submodular games, especially against replication.

Mini-batch gradient descent based methods are the de facto algorithms for training neural network architectures today. We introduce a mini-batch selection strategy based on submodular function maximization. Our novel submodular formulation captures the informativeness of each sample and diversity of the whole subset. W…

In this paper, we study the problem of monotone (weakly) DR-submodular continuous maximization. While previous methods require the gradient information of the objective function, we propose a derivative-free algorithm LDGM for the first time. We define $β$ and $α$ to characterize how close a function is to continuous D…

The paper studies continuous submodular functions and their optimization.

New neural network approach using mutual information.

Paper describes profiles of multivariate normal distributions and novel estimators for mutual information.

Improved bounds on learning algorithms' performance using conditional mutual information.

Paper benchmarks mutual info estimators on diverse distributions.

A new algorithm ThreeSieves maximizes submodular functions efficiently in streaming data.

The paper argues that normalized mutual information is biased in clustering and community detection.

Submodularity is studied for convex risk measures, including Expected Shortfall.

New method for probabilistic modeling of integer submodular functions.

Neural estimator improves mutual information estimation in high dimensions.

In this paper we develop the first algorithms for online submodular minimization that preserve differential privacy under full information feedback and bandit feedback. A sequence of $T$ submodular functions over a collection of $n$ elements arrive online, and at each timestep the algorithm must choose a subset of $[n]…

New algorithm for online convex minimization over integer lattice.

We find the maximum mutual information for neural networks and its key determinants.

Measuring mutual information from finite data is difficult. Recent work has considered variational methods maximizing a lower bound. In this paper, we prove that serious statistical limitations are inherent to any method of measuring mutual information. More specifically, we show that any distribution-free high-confide…

Improved method for encoding contingency tables reduces mutual information bias.

Submodular function minimization is well studied, and existing algorithms solve it exactly or up to arbitrary accuracy. However, in many applications, such as structured sparse learning or batch Bayesian optimization, the objective function is not exactly submodular, but close. In this case, no theoretical guarantees e…

Proposes a new bound on generalization error using conditional mutual information.

Differentially private algorithms for submodular maximization under various constraints.

Proposes a framework to maximize mutual information in VAE models for better latent code representation.

Online optimization has been a successful framework for solving large-scale problems under computational constraints and partial information. Current methods for online convex optimization require either a projection or exact gradient computation at each step, both of which can be prohibitively expensive for large-scal…

Approximate inference via information projection has been recently introduced as a general-purpose approach for efficient probabilistic inference given sparse variables. This manuscript goes beyond classical sparsity by proposing efficient algorithms for approximate inference via information projection that are applica…

We introduce the Mutual Information Machine (MIM), a novel formulation of representation learning, using a joint distribution over the observations and latent state in an encoder/decoder framework. Our key principles are symmetry and mutual information, where symmetry encourages the encoder and decoder to learn differe…

We introduce a method to learn a mixture of submodular "shells" in a large-margin setting. A submodular shell is an abstract submodular function that can be instantiated with a ground set and a set of parameters to produce a submodular function. A mixture of such shells can then also be so instantiated to produce a mor…

A new method estimates mutual information using neural classifiers.

New estimator improves mutual information estimation.

The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.

Paper proposes mutual information learning for deep learning classifiers.

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 l…

New algorithm maximizes non-monotone adaptive submodular functions in linear time.

A new kernel for ranked data tackles computational challenges.

We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutual Information Neural Estimator (MINE) that is linearly scalable in dimensionality as well as in sample size, trainable through back-prop, an…