Dan Ventura

ECAI Conference 2025 Conference Paper

Distilling Reinforcement Learning into Single-Batch Datasets

• Connor Wilhelm
• Dan Ventura

Dataset distillation compresses a large dataset into a small synthetic dataset such that learning on the synthetic dataset approximates learning on the original. Training on the distilled dataset can be performed in as little as one step of gradient descent. We demonstrate that distillation is generalizable to different tasks by distilling reinforcement learning environments into one-batch supervised learning datasets. This demonstrates not only distillation’s ability to compress a reinforcement learning task but also its ability to transform one learning modality (reinforcement learning) into another (supervised learning). We present a novel extension of proximal policy optimization for meta-learning and use it to distill a multi-dimensional extension of the classic cart-pole problem, all MuJoCo environments, and several Atari games. We demonstrate distillation’s ability to compress complex RL environments into one-step supervised learning, explore distillation’s generalizability across agent architectures, and demonstrate distilling an environment into the smallest possible synthetic dataset.

IJCAI Conference 2024 Conference Paper

Musical Phrase Segmentation via Grammatical Induction

• Reed Perkins
• Dan Ventura

We outline a solution to the challenge of musical phrase segmentation that uses grammatical induction algorithms, a class of algorithms which infer a context-free grammar from an input sequence. We analyze the performance of five grammatical induction algorithms on three datasets using various musical viewpoint combinations. Our experiments show that the LONGESTFIRST algorithm achieves the best F1 scores across all three datasets and that input encodings that include the duration viewpoint result in the best performance.

AAAI Conference 2024 Conference Paper

Operationalizing Essential Characteristics of Creativity in a Computational System for Music Composition

• Paul M. Bodily
• Dan Ventura

We address the problem of building and evaluating a computational system whose primary objective is creativity. We illustrate seven characteristics for computational creativity in the context of a system that autonomously composes Western lyrical music. We conduct an external evaluation of the system in which respondents rated the system with regard to each characteristic as well as with regard to overall creativity. Average scores for overall creativity exceeded the ratings for any single characteristic, suggesting that creativity may be an emergent property and that unique research opportunities exist for building CC systems whose design attempts to comprehend all known characteristics of creativity.

AAAI Conference 2016 Conference Paper

Creating Images by Learning Image Semantics Using Vector Space Models

• Derrall Heath
• Dan Ventura

When dealing with images and semantics, most computational systems attempt to automatically extract meaning from images. Here we attempt to go the other direction and autonomously create images that communicate concepts. We present an enhanced semantic model that is used to generate novel images that convey meaning. We employ a vector space model and a large corpus to learn vector representations of words and then train the semantic model to predict word vectors that could describe a given image. Once trained, the model autonomously guides the process of rendering images that convey particular concepts. A significant contribution is that, because of the semantic associations encoded in these word vectors, we can also render images that convey concepts on which the model was not explicitly trained. We evaluate the semantic model with an image clustering technique and demonstrate that the model is successful in creating images that communicate semantic relationships.

IJCAI Conference 2015 Conference Paper

Greedy Structure Search for Sum-Product Networks

• Aaron Dennis
• Dan Ventura

Sum-product networks (SPNs) are rooted, directed acyclic graphs (DAGs) of sum and product nodes with well-defined probabilistic semantics. Moreover, exact inference in the distribution represented by an SPN is guaranteed to take linear time in the size of the DAG. In this paper we introduce an algorithm that learns the structure of an SPN using a greedy search approach. It incorporates methods used in a previous SPN structure-learning algorithm, but, unlike the previous algorithm, is not limited to learning tree-structured SPNs. Several proven ideas from circuit complexity theory along with our experimental results provide evidence for the advantages of SPNs with less-restrictive, nontree structures.

TIST Journal 2014 Journal Article

Conveying Semantics through Visual Metaphor

• Derrall Heath
• David Norton
• Dan Ventura

In the field of visual art, metaphor is a way to communicate meaning to the viewer. We present a computational system for communicating visual metaphor that can identify adjectives for describing an image based on a low-level visual feature representation of the image. We show that the system can use this visual-linguistic association to render source images that convey the meaning of adjectives in a way consistent with human understanding. Our conclusions are based on a detailed analysis of how the system's artifacts cluster, how these clusters correspond to the semantic relationships of adjectives as documented in WordNet, and how these clusters correspond to human opinion.

NeurIPS Conference 2012 Conference Paper

Learning the Architecture of Sum-Product Networks Using Clustering on Variables

• Aaron Dennis
• Dan Ventura

The sum-product network (SPN) is a recently-proposed deep model consisting of a network of sum and product nodes, and has been shown to be competitive with state-of-the-art deep models on certain difficult tasks such as image completion. Designing an SPN network architecture that is suitable for the task at hand is an open question. We propose an algorithm for learning the SPN architecture from data. The idea is to cluster variables (as opposed to data instances) in order to identify variable subsets that strongly interact with one another. Nodes in the SPN network are then allocated towards explaining these interactions. Experimental evidence shows that learning the SPN architecture significantly improves its performance compared to using a previously-proposed static architecture.

IJCAI Conference 2009 Conference Paper

• Adam Drake
• Dan Ventura

Fourier-based learning algorithms rely on being able to efficiently find the large coefficients of a function’s spectral representation. In this paper, we introduce and analyze techniques for finding large coefficients. We show how a previously introduced search technique can be generalized from the Boolean case to the real-valued case, and we apply it in branch-and-bound and beam search algorithms that have significant advantages over the best-first algorithm in which the technique was originally introduced.

AAAI Conference 2008 Conference Paper

Data-Driven Programming and Behavior for Autonomous Virtual Characters

• Jonathan Dinerstein
• Dan Ventura

IJCAI Conference 2007 Conference Paper

• Jonathan Dinerstein
• Parris K. Egbert
• Dan Ventura

Although many powerful AI and machine learning techniques exist, it remains difficult to quickly create AI for embodied virtual agents that produces visually lifelike behavior. This is important for applications (e. g. , games, simulators, interactive displays) where an agent must behave in a manner that appears human-like. We present a novel technique for learning reactive policies that mimic demonstrated human behavior. The user demonstrates the desired behavior by dictating the agent's actions during an interactive animation. Later, when the agent is to behave autonomously, the recorded data is generalized to form a continuous state-to-action mapping. Combined with an appropriate animation algorithm (e. g. , motion capture), the learned policies realize stylized and natural-looking agent behavior. We empirically demonstrate the efficacy of our technique for quickly producing policies which result in lifelike virtual agent behavior.

IJCAI Conference 2007 Conference Paper

• Nancy Fulda
• Dan Ventura

We present a conceptual framework for creating Q-learning-based algorithms that converge to optimal equilibria in cooperative multiagent settings. This framework includes a set of conditions that are sufficient to guarantee optimal system performance. We demonstrate the efficacy of the framework by using it to analyze several well-known multi-agent learning algorithms and conclude by employing it as a design tool to construct a simple, novel multiagent learning algorithm.

NeurIPS Conference 2007 Conference Paper

Iterative Non-linear Dimensionality Reduction with Manifold Sculpting

• Michael Gashler
• Dan Ventura
• Tony Martinez

Many algorithms have been recently developed for reducing dimensionality by projecting data onto an intrinsic non-linear manifold. Unfortunately, existing algo- rithms often lose significant precision in this transformation. Manifold Sculpting is a new algorithm that iteratively reduces dimensionality by simulating surface tension in local neighborhoods. We present several experiments that show Man- ifold Sculpting yields more accurate results than existing algorithms with both generated and natural data-sets. Manifold Sculpting is also able to benefit from both prior dimensionality reduction efforts.

ICML Conference 2005 Conference Paper

A practical generalization of Fourier-based learning

• Adam Drake
• Dan Ventura

NeurIPS Conference 2003 Conference Paper

Training a Quantum Neural Network

• Bob Ricks
• Dan Ventura

Most proposals for quantum neural networks have skipped over the prob- lem of how to train the networks. The mechanics of quantum computing are different enough from classical computing that the issue of training should be treated in detail. We propose a simple quantum neural network and a training method for it. It can be shown that this algorithm works in quantum systems. Results on several real-world data sets show that this algorithm can train the proposed quantum neural networks, and that it has some advantages over classical learning algorithms.