Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression

• URL: http://arxiv.org/abs/2602.08885v3
• Date: Wed, 11 Feb 2026 16:18:37 GMT
• Title: Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression
• Authors: Paul Saegert, Ullrich Köthe,
• Abstract summary: SimpliPy is a rule-based simplification engine achieving a 100-fold speed-up over SymPy at comparable quality.<n>We demonstrate these advantages in our Flash-ANSR framework, which achieves much better accuracy than amortized baselines.
• Score: 8.351253396371686
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Symbolic regression (SR) aims to discover interpretable analytical expressions that accurately describe observed data. Amortized SR promises to be much more efficient than the predominant genetic programming SR methods, but currently struggles to scale to realistic scientific complexity. We find that a key obstacle is the lack of a fast reduction of equivalent expressions to a concise normalized form. Amortized SR has addressed this by general-purpose Computer Algebra Systems (CAS) like SymPy, but the high computational cost severely limits training and inference speed. We propose SimpliPy, a rule-based simplification engine achieving a 100-fold speed-up over SymPy at comparable quality. This enables substantial improvements in amortized SR, including scalability to much larger training sets, more efficient use of the per-expression token budget, and systematic training set decontamination with respect to equivalent test expressions. We demonstrate these advantages in our Flash-ANSR framework, which achieves much better accuracy than amortized baselines (NeSymReS, E2E) on the FastSRB benchmark. Moreover, it performs on par with state-of-the-art direct optimization (PySR) while recovering more concise instead of more complex expressions with increasing inference budget.

Related papers

• Implicit Neural Representation-Based Continuous Single Image Super Resolution: An Empirical Study [50.15623093332659]
  Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR)<n>We compare existing techniques across diverse settings and present aggregated performance results on multiple image quality metrics.<n>We examine a new loss function that penalizes intensity variations while preserving edges, textures, and finer details during training.
  arXiv  Detail & Related papers  (2026-01-25T07:09:20Z)
• Unleashing Degradation-Carrying Features in Symmetric U-Net: Simpler and Stronger Baselines for All-in-One Image Restoration [52.82397287366076]
  All-in-one image restoration aims to handle diverse degradations (e.g., noise, blur, adverse weather) within a unified framework.<n>In this work, we reveal a critical insight: well-crafted feature extraction inherently encodes degradation-carrying information.<n>Our symmetric design preserves intrinsic degradation signals robustly, rendering simple additive fusion in skip connections.
  arXiv  Detail & Related papers  (2025-12-11T12:20:31Z)
• Current Challenges of Symbolic Regression: Optimization, Selection, Model Simplification, and Benchmarking [0.0]
  Symbolic Regression (SR) aims to discover mathematical expressions that describe the relationship between variables.<n>Current methods must be constantly re-evaluated to understand the SR landscape.<n>This thesis addresses these challenges through a sequence of studies conducted throughout the doctorate.
  arXiv  Detail & Related papers  (2025-12-01T13:48:07Z)
• Unlocking Symbol-Level Precoding Efficiency Through Tensor Equivariant Neural Network [84.22115118596741]
  We propose an end-to-end deep learning (DL) framework with low inference complexity for symbol-level precoding.<n>We show that the proposed framework captures substantial performance gains of optimal SLP, while achieving an approximately 80-times speedup over conventional methods.
  arXiv  Detail & Related papers  (2025-10-02T15:15:50Z)
• Sparse Interpretable Deep Learning with LIES Networks for Symbolic Regression [22.345828337550575]
  Symbolic regression aims to discover closed-form mathematical expressions that accurately describe data.<n>Existing SR methods often rely on population-based search or autoregressive modeling.<n>We introduce LIES (Logarithm, Identity, Exponential, Sine), a fixed neural network architecture with interpretable primitive activations that are optimized to model symbolic expressions.
  arXiv  Detail & Related papers  (2025-06-09T22:05:53Z)
• AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution [50.584551250242235]
  AdaptSR is a low-rank adaptation framework that efficiently repurposes bi-cubic-trained SR models for real-world tasks.<n>Our experiments demonstrate that AdaptSR outperforms GAN and diffusion-based SR methods by up to 4 dB in PSNR and 2% in perceptual scores on real SR benchmarks.
  arXiv  Detail & Related papers  (2025-03-10T18:03:18Z)
• Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$ [2.222138965069487]
  Symbolic regression (SR) is a powerful technique for discovering symbolic expressions that characterize nonlinear relationships in data.<n>Existing SR methods do not scale to datasets with a large number of input variables, which is common in modern scientific applications.<n>We propose PAN+SR, which combines ab initio nonparametric variable selection with SR to efficiently pre-screen large input spaces.
  arXiv  Detail & Related papers  (2024-10-17T15:41:06Z)
• Efficient Single Image Super-Resolution with Entropy Attention and Receptive Field Augmentation [34.50541063621832]
  We present an efficient single image super-resolution (SISR) model composed of a novel entropy attention (EA) and a shifting large kernel attention (SLKA) EA increases the entropy of intermediate features conditioned on a Gaussian distribution, providing more informative input for subsequent reasoning. SLKA extends the receptive field of SR models with the assistance of channel shifting, which also favors to boost the diversity of hierarchical features.
  arXiv  Detail & Related papers  (2024-08-08T02:03:10Z)
• Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach [58.57026686186709]
  We introduce the Convolutional Transformer layer (ConvFormer) and propose a ConvFormer-based Super-Resolution network (CFSR) CFSR inherits the advantages of both convolution-based and transformer-based approaches. Experiments demonstrate that CFSR strikes an optimal balance between computational cost and performance.
  arXiv  Detail & Related papers  (2024-01-11T03:08:00Z)
• Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study [25.58608455210458]
  Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. This article explores different approaches that may be deployed during the fine-tuning to reduce the computations needed in the SSL encoder.
  arXiv  Detail & Related papers  (2023-03-12T19:52:34Z)
• FasterPose: A Faster Simple Baseline for Human Pose Estimation [65.8413964785972]
  We propose a design paradigm for cost-effective network with LR representation for efficient pose estimation, named FasterPose. We study the training behavior of FasterPose, and formulate a novel regressive cross-entropy (RCE) loss function for accelerating the convergence. Compared with the previously dominant network of pose estimation, our method reduces 58% of the FLOPs and simultaneously gains 1.3% improvement of accuracy.
  arXiv  Detail & Related papers  (2021-07-07T13:39:08Z)
• Fast Distributionally Robust Learning with Variance Reduced Min-Max Optimization [85.84019017587477]
  Distributionally robust supervised learning is emerging as a key paradigm for building reliable machine learning systems for real-world applications. Existing algorithms for solving Wasserstein DRSL involve solving complex subproblems or fail to make use of gradients. We revisit Wasserstein DRSL through the lens of min-max optimization and derive scalable and efficiently implementable extra-gradient algorithms.
  arXiv  Detail & Related papers  (2021-04-27T16:56:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.