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.
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.
New approach generates optimal disturbances for controller verification.
problem Optimizing disturbances for controller verification with blackbox access.
method Online learning approach that adaptively generates disturbances based on controller inputs.
result New algorithm (MOTR) outperforms existing methods in simulated examples.
SafePILCO is a Python tool for safe reinforcement learning.
problem Safe and efficient policy synthesis in reinforcement learning.
method Extends PILCO algorithm with safety features, implemented in Python.
result Safe and data-efficient policy synthesis achieved.
Paper certifies neural network control policies against persistent adversarial perturbations.
problem Neural networks' fragility to adversarial perturbations in control systems.
method Combining neural network certification tools with robust control theory.
result Certifies neural network policies in a control loop under l-infinity norm bounded adversarial perturbations.
VIPER learns verifiable decision tree policies from deep reinforcement learning.
problem Ensuring safety of learned reinforcement learning policies.
method VIPER combines model compression and imitation learning to train decision tree policies.
result VIPER learns decision tree policies that are provably robust and stable.
New framework verifies reinforcement learning systems without altering neural networks.
problem Lack of assurance guarantees in reinforcement learning applications.
method Repurposes formal verification techniques for reinforcement learning, synthesizing simpler programs that preserve safety.
result Synthesized programs ensure safety of reinforcement learning systems without modifying neural networks.
PIRL generates interpretable reinforcement learning policies using programming languages.
problem Creating interpretable reinforcement learning policies.
method Neurally Directed Program Search (NDPS) for finding optimal programmatic policies.
result PIRL discovers human-readable, smoother, and transferable policies.
PROPEL learns interpretable programmatic policies using imitation and projection.
problem Learning interpretable programmatic policies in reinforcement learning.
method PROPEL is a meta-algorithm based on three insights: optimization in policy space, neural-program mixing, and imitation synthesis.
result PROPEL significantly outperforms state-of-the-art approaches in learning programmatic policies.
The paper uses RL to verify hypotheses, overcoming existing limitations.
problem Verifying hypotheses using reinforcement learning.
method Formulated hypothesis verification as an RL problem, exploiting hypothesis structure.
result RL agents can successfully verify hypotheses, even those not factorizable.
Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world systems. As a consequence, learning algorithms are rarely applied on safety-crit…
Enhances large language models' reasoning through simpler off-policy reinforcement learning.
problem Improving large language models' ability to reason and solve problems.
method EM Policy Gradient, optimizing expected return over reasoning trajectories using Expectation-Maximization (EM) optimization.
result Achieves comparable or slightly superior performance to state-of-the-art methods on reasoning datasets, with additional cognitive behaviors.
VERAFI improves financial AI by verifying calculations and compliance.
problem Financial AI systems generate errors and violations during reasoning.
method VERAFI combines dense retrieval, reranking, and automated reasoning policies.
result VERAFI achieves 94.7% factual correctness, 81% relative improvement.
EEG signals enhance speaker verification system robustness.
problem Improving speaker verification in noisy environments.
method Used end-to-end deep learning model with EEG and speech features.
result EEG signals improve speaker verification robustness, especially in noisy conditions.
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.
Develops a control framework for systemic risk under uncertainty.
problem Systemic risk under model uncertainty.
method Linear-quadratic mean-field control framework with viscosity solutions and verification theorems.
result Explicit feedback controls derived from a coupled Riccati system, preserving analytical tractability.
SIMPOL solves complex economic models using numerical methods.
problem Optimizing consumption and savings under uncertainty.
method SIMPOL uses a modular numerical framework combining policy iteration and finite difference schemes.
result SIMPOL produces solutions consistent with economic and mathematical theory.
In this paper, we assume an insure is allowed to purchase proportional reinsurance and can invest his or her wealth into the financial market where a savings account, stocks and bonds are available. Different from classical optimal investment and reinsurance problem, this paper studies the insurer's long-term investmen…
The trade-off between the cost of acquiring and processing data, and uncertainty due to a lack of data is fundamental in machine learning. A basic instance of this trade-off is the problem of deciding when to make noisy and costly observations of a discrete-time Gaussian random walk, so as to minimise the posterior var…
Develops first robustness verification for complex Transformers.
problem Certify prediction behavior of Transformers with complex self-attention layers.
method Resolves challenges of cross-nonlinearity and cross-position dependency in Transformers.
result Certified robustness bounds are significantly tighter than Interval Bound Propagation.
RL algorithm uses LTL to specify goals for MDPs, ensuring policy satisfaction.
problem Ensuring safety-critical RL policies meet specified goals formally.
method Formulates goals using LTL, translates to LDGBA, shapes synchronous reward function.
result Algorithm synthesizes policies satisfying LTL goals with maximal probability.
Paper develops PAC verification for hypothesis classes and statistical algorithms.
problem Verifying machine learning models interactively.
method Develops interactive proof for PAC verification, proves lower bounds, and introduces a generalization.
result Improved protocol for verifying unions of intervals and statistical query algorithms.
This paper examines the dividend and investment policies of a cash constrained firm that has access to costly external funding. We depart from the literature by allowing the firm to issue collateralized debt to increase its investment in productive assets resulting in a performance sensitive interest rate on debt. We f…
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.
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.
In this article we extend earlier work on the jump-diffusion risk-sensitive asset management problem [SIAM J. Fin. Math. (2011) 22-54] by allowing jumps in both the factor process and the asset prices, as well as stochastic volatility and investment constraints. In this case, the HJB equation is a partial integro-diffe…
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) verifications. Improved speaker verification with condition-aware backend.
problem Speaker verification calibration issues under unknown conditions.
method Discriminative PLDA model with joint training and condition integration.
result Out-of-the-box excellent calibration performance.
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.
We consider a model of optimal investment and consumption with both habit formation and partial observations in incomplete Itô processes market. The investor chooses his consumption under the addictive habits constraint while only observing the market stock prices but not the instantaneous rate of return. Applying the …
Model cash management under ambiguity using maxmin preferences and diffusion.
problem Optimizing cash reserves in the presence of ambiguity.
method Singular control model with maxmin preferences, verified using Dynkin games.
result Higher expected costs and narrower inaction region under increased ambiguity.
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.
Paper tackles speaker verification by removing reverberation using deep LSTM networks.
problem Improving speaker verification accuracy in reverberant environments.
method Dual-label deep LSTM networks trained to map reverberant to clean speech features.
result Evaluates performance using EERs, showing improved accuracy.
New neural network boosts authorship verification on social media.
problem Challenges in verifying authorship of short, diverse social media messages.
method Proposes a new neural network topology for similarity learning.
result Significantly improved performance on author verification tasks.
AgensFlow learns multi-agent coordination policies from experience.
problem Difficult coordination choices in multi-agent systems built on LLMs.
method Online policy learning from repeated trajectories, treating decisions as learnable.
result Learned routing improves coordination-heavy workflows over static wiring.
New framework verifies neural networks with scalable guarantees.
problem Formal verification of neural networks with provable guarantees.
method Formulated as an optimization problem, solved with Lagrangian relaxation.
result Developed algorithms with tightness guarantees under special assumptions.
End-to-end speaker verification framework reduces text dependency.
problem Improving text-independent speaker verification.
method Jointly trains SE and ASR networks with triplet loss and adversarial gradient.
result Lower equal error rate and better text-independency compared to other approaches.
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.
We consider in this paper the optimal dividend problem for an insurance company whose uncontrolled reserve process evolves as a classical Cramér--Lundberg process. The firm has the option of investing part of the surplus in a Black--Scholes financial market. The objective is to find a strategy consisting of both invest…
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 ℓp-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.
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.
New technique reduces verification time for neural networks.
problem Verifying neural networks for safety-critical applications.
method Shadow prices for more efficient input partitioning.
result Significant reduction in computation times for verification.
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 L∞-norm and pseudo-polynomial time for Lp-norm verification. result Polynomial time verification for L∞-norm attackers, NP-hard for other norms, and pseudo-polynomial time for Lp-norm verification. Accelerating Speculative Diffusions via Block Verification
problem Adapting speculative decoding for continuous diffusion models
method Introducing a novel speculative sampling mechanism for diffusion models
result Improves acceptance rate and speeds up inference