Deep Discriminative to Kernel Density Networks for Calibrated Inference

1 code implementation • 31 Jan 2022 • Jayanta Dey, Will LeVine, Haoyin Xu, Ashwin De Silva, Tyler M. Tomita, Ali Geisa, Tiffany Chu, Jacob Desman, Joshua T. Vogelstein

In this paper, we leveraged the fact that deep models, including both random forests and deep-nets, learn internal representations which are unions of polytopes with affine activation functions to conceptualize them both as partitioning rules of the feature space.

Out-of-Distribution Detection regression

Simplest Streaming Trees

2 code implementations • 16 Oct 2021 • Haoyin Xu, Jayanta Dey, Sambit Panda, Joshua T. Vogelstein

In a benchmark suite containing 72 classification problems (the OpenML-CC18 data suite), we illustrate that our approach, Stream Decision Forest (SDF), does not suffer from either of the aforementioned limitations.

Continual Learning Transfer Learning

When are Deep Networks really better than Decision Forests at small sample sizes, and how?

2 code implementations • 31 Aug 2021 • Haoyin Xu, Kaleab A. Kinfu, Will LeVine, Sambit Panda, Jayanta Dey, Michael Ainsworth, Yu-Chung Peng, Madi Kusmanov, Florian Engert, Christopher M. White, Joshua T. Vogelstein, Carey E. Priebe

Empirically, we compare these two strategies on hundreds of tabular data settings, as well as several vision and auditory settings.

Omnidirectional Transfer for Quasilinear Lifelong Learning

1 code implementation • 27 Apr 2020 • Joshua T. Vogelstein, Jayanta Dey, Hayden S. Helm, Will LeVine, Ronak D. Mehta, Ali Geisa, Haoyin Xu, Gido M. van de Ven, Emily Chang, Chenyu Gao, Weiwei Yang, Bryan Tower, Jonathan Larson, Christopher M. White, Carey E. Priebe

But striving to avoid forgetting sets the goal unnecessarily low: the goal of lifelong learning, whether biological or artificial, should be to improve performance on all tasks (including past and future) with any new data.

Federated Learning Transfer Learning