paper-with-me

Papers

Learning Implicitly with Noisy Data in Linear Arithmetic

2020-10-23 · Alexander P. Rader, Ionela G. Mocanu, Vaishak Belle, Brendan Juba

Robust learning in expressive languages with real-world data continues to be a challenging task. Numerous conventional methods appeal to heuristics without any assurances of robustness. While probably approximately correct (PAC) Semantics offers strong guarantees, learning explicit representations is not tractable, even in propositional logic. However, recent work on so-called "implicit" learning has shown tremendous promise in terms of obtaining polynomial-time results for fragments of first-order logic. In this work, we extend implicit learning in PAC-Semantics to handle noisy data in the form of intervals and threshold uncertainty in the language of linear arithmetic. We prove that our extended framework keeps the existing polynomial-time complexity guarantees. Furthermore, we provide the first empirical investigation of this hitherto purely theoretical framework. Using benchmark problems, we show that our implicit approach to learning optimal linear programming objective constraints significantly outperforms an explicit approach in practice.

📄 PDF Abstract BibTeX arXiv:2010.12619

Code (1)

APRader/pac-smt-arithmetic 공식 구현

Similar Papers 제목 키워드 기반

Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems

2022-10-11 · Fan Zhou, Haoyu Dong, Qian Liu, Zhoujun Cheng 외

Numerical reasoning over natural language has been a long-standing goal for the research community. However, cutting-edge language models have proven difficult to reliably generalize to a broad range of numbers, although…

Latent Transformations via NeuralODEs for GAN-based Image Editing

2021-11-29 · ICCV 2021 10 · Valentin Khrulkov, Leyla Mirvakhabova, Ivan Oseledets, Artem Babenko

Recent advances in high-fidelity semantic image editing heavily rely on the presumably disentangled latent spaces of the state-of-the-art generative models, such as StyleGAN. Specifically, recent works show that it is po…

Attribute

Quasi-random Multi-Sample Inference for Large Language Models

2024-11-09 · Aditya Parashar, Aditya Vikram Singh, Avinash Amballa, Jinlin Lai 외

Large language models (LLMs) are often equipped with multi-sample decoding strategies. An LLM implicitly defines an arithmetic code book, facilitating efficient and embarrassingly parallelizable \textbf{arithmetic sampli…

DiversityGSM8KMachine TranslationText Generation+1

iNALU: Improved Neural Arithmetic Logic Unit

2020-03-17 · Daniel Schlör, Markus Ring, Andreas Hotho

Neural networks have to capture mathematical relationships in order to learn various tasks. They approximate these relations implicitly and therefore often do not generalize well. The recently proposed Neural Arithmetic …

DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression

2019-05-15 · Simon Wiedemann, Heiner Kirchhoffer, Stefan Matlage, Paul Haase 외

We present DeepCABAC, a novel context-adaptive binary arithmetic coder for compressing deep neural networks. It quantizes each weight parameter by minimizing a weighted rate-distortion function, which implicitly takes th…

Neural Network CompressionQuantization