Candidate-View Dependence (background)

1 Candidate-View Dependence

Candidate views can be treated as a finite set rather than unrelated rows; set-modeling literature provides useful background [1], [2], [3]. This page does not own the ARIA-NBV equations, model contract, or implementation policy.

The current thesis treatment and evidence boundary are in Typst thesis. Executable model interfaces and duplicate-row/valid-count checks are owned by Python docstrings and tests. Use candidate sampling and SCONE/FisherRF literature for navigation.

Back to top

References

[1]
M. Zaheer, S. Kottur, S. Ravanbakhsh, B. Poczos, R. Salakhutdinov, and A. J. Smola, “Deep sets,” in Advances in neural information processing systems, 2017. Available: https://papers.nips.cc/paper_files/paper/2017/hash/f22e4747da1aa27e363d86d40ff442fe-Abstract.html
[2]
J. Lee, Y. Lee, J. Kim, A. R. Kosiorek, S. Choi, and Y. W. Teh, “Set transformer: A framework for attention-based permutation-invariant neural networks,” in Proceedings of the 36th international conference on machine learning, in Proceedings of machine learning research, vol. 97. PMLR, 2019, pp. 3744–3753. Available: https://proceedings.mlr.press/v97/lee19d.html
[3]
M. M. Bronstein, J. Bruna, T. Cohen, and P. Veličković, “Geometric deep learning: Grids, groups, graphs, geodesics, and gauges.” 2021. Available: https://arxiv.org/abs/2104.13478