Robustifying Algorithms of Learning Latent Trees with Vector Variables

• URL: http://arxiv.org/abs/2106.00885v2
• Date: Thu, 3 Jun 2021 07:23:19 GMT
• Title: Robustifying Algorithms of Learning Latent Trees with Vector Variables
• Authors: Fengzhuo Zhang, Vincent Y. F. Tan
• Abstract summary: We present the sample complexities of Recursive Grouping (RG) and Chow-Liu Recursive Grouping (CLRG) We robustify RG, CLRG, Neighbor Joining (NJ) and Spectral NJ (SNJ) by using the truncated inner product. We derive the first known instance-dependent impossibility result for structure learning of latent trees.
• Score: 92.18777020401484
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider learning the structures of Gaussian latent tree models with vector observations when a subset of them are arbitrarily corrupted. First, we present the sample complexities of Recursive Grouping (RG) and Chow-Liu Recursive Grouping (CLRG) without the assumption that the effective depth is bounded in the number of observed nodes, significantly generalizing the results in Choi et al. (2011). We show that Chow-Liu initialization in CLRG greatly reduces the sample complexity of RG from being exponential in the diameter of the tree to only logarithmic in the diameter for the hidden Markov model (HMM). Second, we robustify RG, CLRG, Neighbor Joining (NJ) and Spectral NJ (SNJ) by using the truncated inner product. These robustified algorithms can tolerate a number of corruptions up to the square root of the number of clean samples. Finally, we derive the first known instance-dependent impossibility result for structure learning of latent trees. The optimalities of the robust version of CLRG and NJ are verified by comparing their sample complexities and the impossibility result.

Related papers

• Identifying General Mechanism Shifts in Linear Causal Representations [58.6238439611389]
  We consider the linear causal representation learning setting where we observe a linear mixing of $d$ unknown latent factors. Recent work has shown that it is possible to recover the latent factors as well as the underlying structural causal model over them. We provide a surprising identifiability result that it is indeed possible, under some very mild standard assumptions, to identify the set of shifted nodes.
  arXiv  Detail & Related papers  (2024-10-31T15:56:50Z)
• Hierarchical clustering with dot products recovers hidden tree structure [53.68551192799585]
  In this paper we offer a new perspective on the well established agglomerative clustering algorithm, focusing on recovery of hierarchical structure. We recommend a simple variant of the standard algorithm, in which clusters are merged by maximum average dot product and not, for example, by minimum distance or within-cluster variance. We demonstrate that the tree output by this algorithm provides a bona fide estimate of generative hierarchical structure in data, under a generic probabilistic graphical model.
  arXiv  Detail & Related papers  (2023-05-24T11:05:12Z)
• Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner [56.08919422452905]
  We propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR) Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises. We outperform existing benchmarks on premise retrieval and entailment tree generation, with around 300% gain in overall correctness.
  arXiv  Detail & Related papers  (2022-05-18T21:52:11Z)
• Active-LATHE: An Active Learning Algorithm for Boosting the Error Exponent for Learning Homogeneous Ising Trees [75.93186954061943]
  We design and analyze an algorithm that boosts the error exponent by at least 40% when $rho$ is at least $0.8$. Our analysis hinges on judiciously exploiting the minute but detectable statistical variation of the samples to allocate more data to parts of the graph.
  arXiv  Detail & Related papers  (2021-10-27T10:45:21Z)
• Decentralized Learning of Tree-Structured Gaussian Graphical Models from Noisy Data [1.52292571922932]
  This paper studies the decentralized learning of tree-structured Gaussian graphical models (GGMs) from noisy data. GGMs are widely used to model complex networks such as gene regulatory networks and social networks. The proposed decentralized learning uses the Chow-Liu algorithm for estimating the tree-structured GGM.
  arXiv  Detail & Related papers  (2021-09-22T10:41:18Z)
• Spectral Top-Down Recovery of Latent Tree Models [13.681975313065477]
  Spectral Top-Down Recovery (STDR) is a divide-and-conquer approach for inference of large latent tree models. STDR's partitioning step is non-random. Instead, it is based on the Fiedler vector of a suitable Laplacian matrix related to the observed nodes. We prove that STDR is statistically consistent, and bound the number of samples required to accurately recover the tree with high probability.
  arXiv  Detail & Related papers  (2021-02-26T02:47:42Z)
• SGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy Samples [75.32013242448151]
  We consider learning Ising tree models when the observations from the nodes are corrupted by independent but non-identically distributed noise. Katiyar et al. (2020) showed that although the exact tree structure cannot be recovered, one can recover a partial tree structure. We propose Symmetrized Geometric Averaging (SGA), a more statistically robust algorithm for partial tree recovery.
  arXiv  Detail & Related papers  (2021-01-22T01:57:35Z)
• From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering [33.000371053304676]
  We present the first continuous relaxation of Dasgupta's discrete optimization problem with provable quality guarantees. We show that even approximate solutions found with gradient descent have superior quality than agglomerative clusterings. We also highlight the flexibility of HypHC using end-to-end training in a downstream classification task.
  arXiv  Detail & Related papers  (2020-10-01T13:43:19Z)
• Spectral neighbor joining for reconstruction of latent tree models [5.229354894035374]
  We develop Spectral Neighbor Joining, a novel method to recover the structure of latent tree graphical models. We prove that SNJ is consistent, and derive a sufficient condition for correct tree recovery from an estimated similarity matrix. We illustrate via extensive simulations that in comparison to several other reconstruction methods, SNJ requires fewer samples to accurately recover trees with a large number of leaves or long edges.
  arXiv  Detail & Related papers  (2020-02-28T05:13:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.