Asia
Embedding Dimension of Contrastive Learning and k-Nearest Neighbors
We study the embedding dimension of distance comparison data in two settings: contrastive learning and k -nearest neighbors ( k -NN).
e1b248453bca182b6138b8c14a75340d-Paper-Conference.pdf
Intensive algorithmic efforts have been made to enable the rapid improvements of certificated robustness for complex ML models recently. However, current robustness certification methods are only able to certify under a limited perturbation radius. Given that existingpure data-driven statistical approaches have reached a bottleneck, in this paper, we propose to integrate statistical ML modelswithknowledge (expressed aslogical rules) asareasoningcomponent using Markovlogic networks (MLN), so as to further improvethe overall certified robustness.
Non-metric Similarity Graphs for Maximum Inner Product Search
Stanislav Morozov, Artem Babenko
For large-scale databases the sequential scan with theO(nd) complexity is not feasible, and the efficient approximate methods arerequired.
Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models
We find that the ability of LLMs to maintain consistency varies across different moral scenarios.
Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces
Neural Information Processing Systems http://nips.cc/
First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time
For finding a nearly second-orderstationary pointxsuchthatk F(x)k and 2F(x) I (in high probability), the best time complexity of the presented algorithms is eO(d/3.5),whereF(