No article text was recorded for this version.
numerical precision constraints
Version 2 of 2169 papers241 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Expressive Power of ReLU and Step Networks under Floating-Point Operations
- Blog: Formal Aspects of Language Modeling
- Blog: Theoretical Constraints on the Expressive Power of RoPE-based Tensor Attention Transformers
- Blog: On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic
- Blog: Logical characterizations of recurrent graph neural networks with reals and floats
- Blog: On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
- Blog: An Algebraic View of the Expressivity of Recurrent Language Models
- Blog: Tighter Bounds on the Expressivity of Transformer Encoders
- Blog: On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth
- Blog: Formal languages and neural models for learning on sequences
- Blog: On the Power of Saturated Transformers: A View from Circuit Complexity
- Blog: Logical Characterizations of Recurrent Graph Neural Networks with Reals and Floats
- Blog: Tighter Bounds on the Expressivity of Transformer Encoders
- Blog: Structure of universal formulas
- Blog: Transformers in Uniform TC$^0$
- Blog: Analog Neural Networks of Limited Precision I: Computing with Multilinear Threshold Functions
- Blog: On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
- Blog: Length Generalization Bounds for Transformers
- Blog: On the Practical Computational Power of Finite Precision RNNs for Language Recognition
- Blog: On Expressive Power of Floating-Point Transformers
- Blog: Sequential Neural Networks as Automata
- Blog: The phase diagram of approximation rates for deep neural networks
- Blog: Why ReLU? A Bit-Model Dichotomy for Deep Network Training
- Blog: Quantifying The Limits of AI Reasoning: Systematic Neural Network Representations of Algorithms
- Blog: Every Bit Counts: A Theoretical Study of Precision-Expressivity Tradeoffs in Quantized Transformers
- Blog: A Formal Proof of the Expressiveness of Deep Learning
- Blog: Expressive Power of Graph Transformers via Logic
- Blog: Descriptive complexity for neural networks via Boolean networks
- Blog: Structure of universal formulas
- Blog: Analyzing the Power of Chain of Thought through Memorization Capabilities
- Blog: Why Are Linear RNNs More Parallelizable?
- Blog: Fundamental Limits of Crystalline Equivariant Graph Neural Networks: A Circuit Complexity Perspective
- Blog: Mini-Workshop: Mathematics of Entropic AI in the Natural Sciences
- Blog: Deep Network Approximation in Terms of Intrinsic Parameters
- Blog: Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients
- Blog: Analyzing the Power of Chain of Thought through Memorization Capabilities
- Blog: On Minimum Depth and Width of Floating-Point Neural Networks for Representing Floating-Point Functions
- Blog: On the Turing Completeness of Modern Neural Network Architectures
- Blog: Transformers as Recognizers of Formal Languages: A Survey on Expressivity
- Blog: On the Turing Completeness of Modern Neural Network Architectures
- Blog: Constant Bit-size Transformers Are Turing Complete
- Blog: Floating-Point Neural Networks are Provably Robust Universal Approximators
- Blog: Elementary superexpressive activations
- Blog: Provable Memorization via Deep Neural Networks using Sub-linear Parameters
- Blog: The phase diagram of approximation rates for deep neural networks
- Blog: On the Representational Capacity of Recurrent Neural Language Models
- Blog: Neural Network Approximation: Three Hidden Layers Are Enough
- Blog: On the Representational Capacity of Recurrent Neural Language Models
- Blog: On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective
- Blog: Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
- Blog: The Sample Complexity of Stackelberg Games
- Blog: Metric Automata Theory: A Unifying Theory of RNNs
- Blog: Constant Bit-size Transformers Are Turing Complete
- Blog: Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers
- Blog: On the Computational Complexity and Formal Hierarchy of Second Order Recurrent Neural Networks
- Blog: Acceleration Meets Inverse Maintenance: Faster ℓ∞-Regression
- Blog: Complexity of Inferences in Polytree-shaped Semi-Qualitative Probabilistic Networks
- Blog: On the Space Complexity of Online Convolution
- Blog: New advances in universal approximation with neural networks of minimal width
- Blog: On the Computational Power of Transformers and Its Implications in Sequence Modeling
Showing 60 of 169 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_numerical_precision_constraints_0695e3e5,
title = {numerical precision constraints},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/numerical-precision-constraints/rdr_0695e3e5a0e64c70a60feee080a59a96},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_numerical_precision_constraints_0695e3e5_v2,
title = {numerical precision constraints},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/numerical-precision-constraints/rdr_0695e3e5a0e64c70a60feee080a59a96/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}