Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

11223243 · Jun 202019922001200920182026
48 results for symbolic verification

NeuroDiff improves neural network equivalence verification with fine-grained approximations.

problem Verifying the equivalence of compressed neural networks.
method Symbolic and fine-grained approximation technique for differential verification.
result NeuroDiff achieves up to 1000X speedup and 5X accuracy improvement.

Revel tackles safe exploration in RL with verified symbolic policies.

problem Computational infeasibility of verifying neural networks in RL learning loops.
method Two policy classes: neurosymbolic with approximate gradients and symbolic policies for efficient verification. Mirror descent over policies to safely update and project policies.
result Revel discovers policies that outperform prior approaches to verified exploration.

Accelerates DNN robustness verification with target labels.

problem Improving the robustness of deep neural networks against adversarial attacks.
method Guiding robustness verification with target labels, reducing search space and using symbolic interval propagation and linear relaxation.
result Significantly improves DNN verification speed by 36X, especially when perturbation distance is reasonable.

Study robustness of polynomial neural networks using algebraic geometry.

problem Certify robustness radius of polynomial neural networks.
method Metric algebraic geometry, Euclidean distance degree, symbolic elimination, homotopy-continuation methods.
result Found decision boundaries with lower ED degree than generic cubic hypersurfaces.

This work improves neural network robustness to symbol substitutions using formal verification.

problem Neural networks' vulnerability to adversarial attacks, especially under discrete text perturbations.
method Formal verification using Interval Bound Propagation on a simplex model of input perturbations.
result Models show improved verified accuracy under perturbations with formal guarantees.

CALVER verifies causal reasoning traces, improving over voting methods in complex queries.

problem Voting fails in causal reasoning due to repeated confounding errors and multiple valid answers.
method CALVER scores structured traces against causal criteria and selects the highest-scoring candidate.
result CALVER selects valid answers more accurately than voting methods, especially with larger sample sizes.

Stability of black holes proven in full subextremal range with positive cosmological constant.

problem Stability of Kerr-de Sitter black holes in the full subextremal range.
method Similar to previous proof in slowly rotating case, with implementation of constraint damping and verification of subprincipal symbol condition.
result Stability of Kerr-de Sitter black holes proven in the full subextremal range.

Transformers learn to predict temporal logic solutions from classical solver outputs.

problem Training neural networks on logic problem solutions for verification.
method Training a Transformer on generated training data from classical solvers, focusing on one solution per formula.
result Transformers can predict correct solutions to temporal logic problems, even to unseen benchmarks.

Formalizes weak and strong verification for LLMs, controlling errors without assumptions.

problem Balancing cost and reliability in reasoning with LLMs.
method Formalizes weak-strong verification policies, introduces metrics, develops online algorithm.
result Optimal policies admit a two-threshold structure, and calibration and sharpness govern value of weak verifiers.

We improve neural network robustness verification by training for faster stability.

problem Efficient verification of adversarial robustness in deep networks.
method Co-design of weight sparsity and ReLU stability to simplify verification.
result Improving ReLU stability leads to a 4-13x speedup in verification times.

Paper optimizes hypothesis verification in sequential experiments.

problem Maximizing confidence in a verified hypothesis after exploration.
method Formulated as a confidence maximization problem in a POMDP, characterized optimal solutions, and proposed a heuristic.
result Heuristic performs better than existing methods in some scenarios.

New methods combat data poisoning attacks in bandit algorithms using limited verification.

problem Data poisoning attacks on bandit algorithms, especially in the UCB and ETC types.
method Verification-based mechanisms to restore optimal regret with limited verifications.
result A simple modified ETC type bandit algorithm can restore optimal regret with O(logT)O(\log T) verifications.

New algorithm speeds up robustness verification for tree-based models.

problem Formal robustness verification of tree-based models, especially ensembles.
method Reformulated as max-clique problem on a multi-partite graph with bounded boxicity; developed efficient multi-level verification algorithm.
result Tight lower bounds on robustness of decision tree ensembles, hundreds of times faster than previous approach.

Improves neural network verification by merging abstract domains and Lagrangian methods.

problem Prove provable bounds for neural network outputs given input ranges.
method Uses zonotopes within a Lagrangian decomposition to verify deep neural networks.
result Yields bounds that improve upon existing techniques in both time and tightness.

This paper explores formal verification for autonomous systems, identifying limitations and proposing improvements.

problem Ensuring safety of autonomous systems like self-driving cars and drones.
method Formal verification techniques based on formal methods, analyzing three assumptions and their limitations.
result Preliminary work to improve the strength of evidence provided by formal verification.

Paper develops a model for verifying facts in tables without pre-retrieved evidence.

problem Verification of factual claims in structured data, especially in open-domain settings.
method Joint reranking-and-verification model that fuses evidence documents.
result Model achieves comparable performance to closed-domain state-of-the-art on TabFact dataset.

Unified framework integrates symbolic planning and HRL for robust decision-making.

problem Combining reinforcement learning and symbolic planning for robust decision-making in dynamic environments.
method Integrates symbolic planning with hierarchical reinforcement learning to guide task execution and improve planning.
result Unified framework leads to rapid policy search and robust symbolic plans in complex domains.

Handwritten signature verification remains challenging, especially offline.

problem Discriminate genuine from forged signatures in static scenarios.
method Review of past research and analysis of recent advancements in Deep Learning.
result Deep Learning has shown promise in feature representation learning from signature images.

Paper proposes an ensemble model for writer-independent offline signature verification using deep learning.

problem Difficulty in distinguishing genuine signatures from skilled forgeries in writer-independent offline signature verification.
method Used an ensemble model with two CNNs for feature extraction, RGBT for classification, and stacking for final prediction.
result Achieved state-of-the-art performance on various datasets.

Efficiently verifies neural networks by handling neuron splits, improving speed and accuracy.

problem Handling neuron split constraints in incomplete neural network verification.
method β-CROWN, which optimizes parameters β to encode neuron splits and uses them in bound propagation.
result β-CROWN significantly speeds up verification while maintaining high accuracy.

Semantify-NN verifies neural network robustness against semantic perturbations.

problem Verifying robustness of neural networks against semantic adversarial attacks.
method Inserting semantic perturbation layers (SP-layers) into neural networks to verify robustness.
result Semantify-NN significantly improves robustness verification performance over p\ell_p-norm-based methods.

Proposes a new neural network for text-dependent speaker verification.

problem Improves speaker verification by encoding phrase and speaker information.
method Uses differentiable alignment models to produce supervectors from utterances.
result Achieves competitive performance in text-dependent speaker verification tasks.

New method for constructing frames for vector distributions with specific symbols.

problem Constructing frames for vector distributions with given Jacobi symbols.
method Introducing Jacobi symbols, Optimal Control ideas, explicit construction of canonical frames, algebraic procedure.
result Explicit construction of canonical frames for all distributions with given Jacobi symbols, description of prolongation algebra for most Jacobi symbols.

We describe dimensionally constrained symbolic regression which has been developed for mass measurement in certain classes of events in high-energy physics (HEP). With symbolic regression, we can derive equations that are well known in HEP. However, in problems with large number of variables, we find that by constraini…

2011-06-20abs ↗pdf ↗

Researchers find floating point errors can mislead neural network verifiers.

problem Floating point arithmetic inaccuracies mislead neural network verifiers.
method Efficiently searches inputs and constructs neural network architectures to exploit verification errors.
result Floating point errors can systematically mislead neural network verifiers.

End-to-end system improves speaker verification using attention mechanism.

problem Improving text-dependent speaker verification accuracy.
method Speaker discriminative CNNs extract features, attention mechanism combines them, end-to-end training optimizes system.
result The proposed system achieves better performance on Windows 10 speaker verification task.

Paper closes neural-symbolic learning loop with grammar model and back-search algorithm.

problem Slow convergence in neural-symbolic learning due to error propagation issues.
method Introduces grammar model as symbolic prior and back-search algorithm for efficient error propagation.
result Significantly outperforms RL methods in performance, converging speed, and data efficiency.

For an arbitrary Riemannian manifold XX and Hermitian vector bundles EE and FF over XX we define the notion of the normal symbol of a pseudodifferential operator PP from EE to FF. The normal symbol of PP is a certain smooth function from the cotangent bundle TXT^*X to the homomorphism bundle Hom(E,F)Hom (E,F) and dep…

1996-12-11abs ↗pdf ↗

This study extends verifiable learning to boosted tree ensembles, enabling efficient security verification.

problem Efficiently verifying the robustness of boosted tree ensembles against norm-based attackers.
method Formal verification of robustness for large-spread boosted tree ensembles, considering LL_\infty-norm and pseudo-polynomial time for LpL_p-norm verification.
result Polynomial time verification for LL_\infty-norm attackers, NP-hard for other norms, and pseudo-polynomial time for LpL_p-norm verification.

Paper proposes a new embedding method for face verification and clustering.

problem Unconstrained face verification remains challenging.
method Coupling deep CNN with triplet probability constraints for low-dimensional embedding.
result The proposed method outperforms state-of-the-art methods in verification and identification metrics.

Unified convex relaxation framework for neural network robustness verification.

problem Inability to achieve tight verification of neural networks against adversarial attacks.
method Unified convex relaxation framework for neural networks of various architectures and nonlinearities.
result Exact solution to convex-relaxed problem does not significantly improve verification gap.

Symbolic dynamics applied to share prices reveals complex, non-Markovian patterns.

problem Analyzing complex systems like share prices using symbolic dynamics.
method Symbolic dynamics applied to time series of share price returns.
result Nontrivial spectrum of Renyi entropies found, indicating non-Markovian behavior.