More Like this

1. PRNet: Self-Supervised Learning for Partial-to-Partial Registration

   Wang, Yue; Solomon, Justin (January 2019, NeurIPS)

   null (Ed.)
2. Mean field approach to stochastic control with partial information

   https://doi.org/10.1051/cocv/2021085  

   Bensoussan, Alain; Yam, Sheung Chi (January 2021, ESAIM: Control, Optimisation and Calculus of Variations)

   Buttazzo, G.; Casas, E.; de Teresa, L.; Glowinski, R.; Leugering, G.; Trélat, E.; Zhang, X. (Ed.)

   In our present article, we follow our way of developing mean field type control theory in our earlier works [Bensoussanet al., Mean Field Games and Mean Field Type Control Theory.Springer, New York (2013)], by first introducing the Bellman and then master equations, the system of Hamilton-Jacobi-Bellman (HJB) and Fokker-Planck (FP) equations, and then tackling them by looking for the semi-explicit solution for the linear quadratic case, especially with an arbitrary initial distribution; such a problem, being left open for long, has not been specifically dealt with in the earlier literature, such as Bensoussan [Stochastic Control of Partially Observable Systems. Cambridge University Press, (1992)] and Nisio [Stochastic control theory: Dynamic programming principle. Springer (2014)], which only tackled the linear quadratic setting with Gaussian initial distributions. Thanks to the effective mean-field theory, we propose a solution to this long standing problem of the general non-Gaussian case. Besides, our problem considered here can be reduced to the model in Bandiniet al.[Stochastic Process. Appl.129(2019) 674–711], which is fundamentally different from our present proposed framework. 

   more » « less
3. A Broadcast Approach to Multiple Access with Partial CSIT

   https://doi.org/10.1109/GLOCOM.2018.8647542  

   Zohdy, Maha; Kazemi, Samia; Tajer, Ali (December 2018, IEEE Global Communications Conference)
4. Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals

   https://doi.org/10.18653/v1/2024.findings-emnlp.205  

   Elazar, Yanai; Paranjape, Bhargavi; Peng, Hao; Wiegreffe, Sarah; Chandu, Khyathi; Srikumar, Vivek; Singh, Sameer; Smith, Noah A (January 2024, Association for Computational Linguistics)

   The inevitable appearance of spurious correlations in training datasets hurts the generalization of NLP models on unseen data. Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the input (e.g., the hypothesis in NLI) and the label; consequently, models trained only on those outperform chance. Are these correlations picked up by models trained on the full input data? To address this question, we propose a new evaluation method, Counterfactual Attentiveness Test (CAT). CAT uses counterfactuals by replacing part of the input with its counterpart from a different example (subject to some restrictions), expecting an attentive model to change its prediction. Using CAT, we systematically investigate established supervised and in-context learning models on ten datasets spanning four tasks: natural language inference, reading comprehension, paraphrase detection, and visual & language reasoning. CAT reveals that reliance on such correlations is mainly data-dependent. Surprisingly, we find that GPT3 becomes less attentive with an increased number of demonstrations, while its accuracy on the test data improves. Our results demonstrate that augmenting training or demonstration data with counterfactuals is effective in improving models’ attentiveness. We show that models’ attentiveness measured by CAT reveals different conclusions from solely measuring correlations in data. 

   more » « less
5. Local Access to Huge Random Objects through Partial Sampling

   Biswas, Amartya Shankha; Rubinfeld, Ronitt; Yodpinyanee, Anak (January 2020, 11th Innovations in Theoretical Computer Science (ITCS 2020))

   Consider an algorithm performing a computation on a huge random object. Is it necessary to generate the entire object up front, or is it possible to provide query access to the object and sample it incrementally "on-the-fly"? Such an implementation should emulate the object by answering queries in a manner consistent with a random instance sampled from the true distribution. Our first set of results focus on undirected graphs with independent edge probabilities, under certain assumptions. Then, we use this to obtain the first efficient implementations for the Erdos-Renyi model and the Stochastic Block model. As in previous local-access implementations for random graphs, we support Vertex-Pair and Next-Neighbor queries. We also introduce a new Random-Neighbor query. Next, we show how to implement random Catalan objects, specifically focusing on Dyck paths (always positive random walks on the integer line). Here, we support Height queries to find the position of the walk, and First-Return queries to find the time when the walk returns to a specified height. This in turn can be used to implement Next-Neighbor queries on random rooted/binary trees, and Matching-Bracket queries on random well bracketed expressions. Finally, we define a new model that: (1) allows multiple independent simultaneous instantiations of the same implementation to be consistent with each other without communication (2) allows us to generate a richer class of random objects that do not have a succinct description. Specifically, we study uniformly random valid q-colorings of an input graph G with max degree Δ. The distribution over valid colorings is specified via a "huge" underlying graph G, that is far too large to be read in sub-linear time. Instead, we access G through local neighborhood probes. We are able to answer queries to the color of any vertex in sub-linear time for q>9Δ. 

   more » « less