Searcharxiv⌕ Search

arXiv subjects

Kevin Miller

Publications and source records attributed to Kevin Miller.

22 records · Page 2Linked to original sources

Efficient Graph-Based Active Learning with Probit Likelihood via Gaussian Approximations

We present a novel adaptation of active learning to graph-based semi-supervised learning (SSL) under non-Gaussian Bayesian models. We present an approximation of non-Gaussian distributions to adapt previously Gaussian-based acquisition functions to these more general cases. We develop an efficient rank-one update for applying "look-ahead" based methods as well as model retraining. We also introduce a novel "model change" acquisition function based on these approximations that further expands the available collection of active learning acquisition functions for such methods.

stat.ML↗

Meta-learning of Sequential Strategies

In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. Our goal is to equip the reader with the conceptual foundations of this tool for building new, scalable agents that operate on broad domains. To do so, we present basic algorithmic templates for building near-optimal predictors and reinforcement learners which behave as if they had a probabilistic model that allowed them to efficiently exploit task structure. Furthermore, we recast memory-based meta-learning within a Bayesian framework, showing that the meta-learned strategies are near-optimal because they amortize Bayes-filtered data, where the adaptation is implemented in the memory dynamics as a state-machine of sufficient statistics. Essentially, memory-based meta-learning translates the hard problem of probabilistic sequential inference into a regression problem.

cs.LG↗

Forward Thinking: Building Deep Random Forests

The success of deep neural networks has inspired many to wonder whether other learners could benefit from deep, layered architectures. We present a general framework called forward thinking for deep learning that generalizes the architectural flexibility and sophistication of deep neural networks while also allowing for (i) different types of learning functions in the network, other than neurons, and (ii) the ability to adaptively deepen the network as needed to improve results. This is done by training one layer at a time, and once a layer is trained, the input data are mapped forward through the layer to create a new learning problem. The process is then repeated, transforming the data through multiple layers, one at a time, rendering a new dataset, which is expected to be better behaved, and on which a final output layer can achieve good performance. In the case where the neurons of deep neural nets are replaced with decision trees, we call the result a Forward Thinking Deep Random Forest (FTDRF). We demonstrate a proof of concept by applying FTDRF on the MNIST dataset. We also provide a general mathematical formulation that allows for other types of deep learning problems to be considered.

stat.ML↗

TCPTuner: Congestion Control Your Way

TCPTuner is a TCP (transmission control protocol) congestion control kernel module and GUI (graphical user interface) for Linux that allows real-time modification of the congestion control parameters of TCP CUBIC, the current default algorithm in Linux. Specifically, the tool provides access to alpha, the rate at which a sender's congestion window grows; beta, the multiplicative factor to decrease the congestion window on a loss event; as well as CUBIC's fast convergence and tcp friendliness parameters. Additionally, the interface provides access to ip-route parameters for the minimum retransmission time and initial congestion window size. In this paper, we describe the implementation of TCPTuner and show experimental data of the effects of adjusting congestion control parameters.

cs.NI↗