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.

168,695 papers · 148 categories

Trend · papers per month

3978117156 · May 202619922001200920172026
48 results for Budget Awareness

SIREN protocol corrects optimistic winner's scores in LLM evaluation.

problem Optimistic winner's scores in LLM evaluation due to adaptive benchmarking.
method SIREN protocol that freezes post-search shortlist, separates selection and evaluation, and uses bootstrap for uncertainty quantification.
result SIREN provides valid confidence intervals for procedure-performance curves and deployment conclusions.

A new method for active learning works well across all label budgets.

problem Active learning methods perform poorly in both low and high label budgets.
method Uncertainty Herding: a simple, computationally fast method that optimizes uncertainty coverage.
result Uncertainty Herding nearly optimizes distribution-level coverage and performs well across various active learning tasks.

ARCO-BO optimizes multi-agent design under heterogeneity, improving efficiency and performance.

problem Heterogeneous multi-agent optimization challenges in resource use and information sharing.
method ARCO-BO integrates a consensus mechanism, budget-aware sampling, and partial input sharing for heterogeneous design spaces.
result ARCO-BO outperforms independent and collaborative BO methods in complex multi-agent settings.

PAC-MCTS addresses biased search in LLM-guided planning by dynamically pruning.

problem Systematic biases in LLMs lead to inefficient and unsafe search in deep planning tasks.
method Formulates node expansion as BAI under bounded bias, derives sample complexity bounds, and proposes PAC-MCTS for dynamic confidence bounds.
result PAC-MCTS improves robustness and efficiency by up to 78% fewer API evaluations and 3x higher sample efficiency.

Suppliers (including companies and individual prosumers) may wish to protect their private information when selling items they have in stock. A market is envisaged where private information can be protected through the use of differential privacy and option contracts, while privacy-aware suppliers deliver their stock a…

2015-09-22abs ↗pdf ↗

Neural Index Policy for multi-action bandits with heterogeneous budgets.

problem Real-world settings often involve multiple interventions with heterogeneous costs and constraints, breaking classical assumptions.
method Introduces a Neural Index Policy (NIP) that learns to assign budget-aware indices to arm-action pairs using a neural network and differentiable knapsack layer.
result Empirically achieves near-optimal performance while strictly enforcing heterogeneous budgets and scaling to hundreds of arms.

AutoScale improves LLM pre-training by adjusting data mixtures at different scales.

problem Data mixtures that work well at small scales may not perform as well at larger scales.
method AutoScale uses a two-stage approach: fitting a model to predict loss under different compositions and extrapolating optimal compositions to larger scales.
result AutoScale accelerates convergence and improves downstream performance.

IUPM monitors machine learning models under gradual shifts using optimal transport and active labeling.

problem Gradual distribution shifts lead to unnoticed accuracy declines in machine learning models.
method Incremental Uncertainty-aware Performance Monitoring (IUPM) using optimal transport and active labeling.
result IUPM outperforms existing baselines in gradual shift scenarios and guides label acquisition more effectively.

HyperSTAR optimizes deep network hyperparameters for specific tasks.

problem Finding optimal hyperparameters for deep neural networks is computationally expensive and task-agnostic approaches are inefficient.
method HyperSTAR learns a dataset representation and a performance predictor from raw images, ranking and recommending hyperparameters conditioned on a joint dataset-hyperparameter space.
result HyperSTAR reduces HPO time by 50% on large-scale image classification datasets.

Quantum computing optimizes ESG portfolios efficiently.

problem Optimizing investment portfolios with risk, return, and ESG considerations.
method Formulated discrete Markowitz portfolio theory (DMPT) for quantum annealers, incorporating ESG ratings.
result Discrete portfolios converge to continuous solutions as budgets increase, outperforming traditional methods.

Framework evaluates AI proposals for drug discovery, finds no LLM advantage.

problem No principled framework exists for evaluating AI-guided scientific selection under budget constraints.
method Formally verified metric (BSDS/DQS) penalizes false discoveries and excessive abstention.
result LLMs provide no marginal value over existing classifiers in drug discovery.

Inference-aware meta-alignment of LLMs reduces computational cost.

problem Aligning LLMs to diverse human preferences is challenging due to conflicting criteria.
method IAMA trains a base model to be aligned to multiple tasks via different inference-time alignment algorithms, using non-linear GRPO for optimization.
result IAMA enables effective alignment of LLMs to multiple criteria with limited computational budget.

Designs efficient factorial experiments for product design under budget constraints.

problem Designing effective experiments for product design with limited traffic and overlapping experiments.
method Two-stage design: first stage samples and infers performance, second stage selects a final policy.
result The method outperforms one-shot tensor completion and unstructured best-arm benchmarks.

Quantum algorithm reduces CVA risk-neutral expectation estimation costs.

problem Reducing Monte Carlo sampling cost for CVA on real quantum hardware.
method Noise-aware quantum workflow combining market calibration, discretisation, and oracle construction.
result CABIQAE achieves lower classical post-processing runtime and more effective error exploitation.

Paper defends deep learning classifiers against channel-aware adversarial attacks.

problem Deep learning classifiers are vulnerable to adversarial attacks.
method Channel-aware adversarial attacks are presented and defended against.
result Certified defense based on randomized smoothing makes classifiers robust.

Unified framework for simulation-based inference learns a single model for multiple tasks.

problem Simulation-based inference for multiple tasks with limited model retraining.
method Unified flow-matching generative model with query-aware masking distribution.
result Competitive performance on various inference tasks and real-world problems.

Bayesian optimization offers a flexible framework to optimize an objective function that is expensive to be evaluated. A Bayesian optimizer iteratively queries the function values on its carefully selected points. Subsequently, it makes a sensible recommendation about where the optimum locates based on its accumulated …

2019-06-22abs ↗pdf ↗

New method defends RL agents from poisoning attacks without MDP knowledge.

problem Poisoning attacks on RL systems can cause learning failures.
method Generic poisoning framework for online RL, Vulnerability-Aware Adversarial Critic Poison (VA2C-P).
result Successfully prevents RL agents from learning good policies or converging to target policies.

InfoTree improves reinforcement learning by optimizing tool use with a greedy submodular approach.

problem Maximizing information from tool use in reinforcement learning with limited resources.
method Formalizes Rollout Informativeness, recasts state selection as submodular maximization, and uses UUCB and ABA.
result InfoTree outperforms existing methods across various benchmarks, improving performance by 18.2% on average.

A new algorithm learns from failures to optimize under constraints efficiently.

problem Optimizing under unknown constraints with limited failure tolerance.
method Excursion search controls risk as a function of a failure budget.
result The algorithm achieves lower regret and uses failures budget more efficiently.

LOFT separates subspace rotation and transformation for orthogonal fine-tuning.

problem Conflating subspace rotation and transformation in orthogonal fine-tuning.
method LOFT explicitly separates subspace rotation and transformation, using task-aware support selection.
result LOFT recovers principal-subspace orthogonal adaptation and improves efficiency-performance trade-off.

Paper proposes EEIPU, a memoization-aware BO algorithm to reduce hyperparameter tuning costs.

problem High costs in GPU-days for training and fine-tuning language models.
method Memoization-aware Bayesian Optimization (EEIPU) algorithm in tandem with pipeline caching.
result EEIPU produces 103% more hyperparameter candidates and 108% more validation metric improvement.

FDN improves probabilistic regressors' adaptability to distribution shifts.

problem Overconfidence in modern probabilistic regressors under distribution shift.
method FDN uses input-conditioned distributions over network weights, trained with a Monte Carlo beta-ELBO objective.
result FDN produces predictive mixtures whose dispersion adapts to the input, providing shift-aware uncertainty.

New method calibrates noise for attack risk, improving ML model accuracy.

problem Improving accuracy of privacy-preserving ML models while maintaining privacy.
method Directly calibrates noise scale to a desired attack risk level, bypassing the standard ε\varepsilon-calibration.
result Significantly decreases noise scale, leading to increased utility at the same risk level.

DQ4FairIM uses RL to maximize influence while ensuring fairness across all groups.

problem Fairness in influence maximization in social networks.
method Fairness-aware deep RL method using Structure2Vec network embedding.
result DQ4FairIM achieves higher fairness than fairness-agnostic and fairness-aware baselines.

New method optimizes language model performance for test-time strategies.

problem Mismatch between training objectives and test-time deployment of large language models.
method Tail-Extrapolated estimators to approximate best-of-N performance from limited training rollouts.
result Improved performance of best-of-N deployment across various models and datasets.

Paper develops a new RL method for MDPs with uncertainty, achieving better regret bounds.

problem Online reinforcement learning in environments with both endogenous and exogenous uncertainty.
method Developed a VB-UCRL algorithm that restarts based on variation schedules.
result Established a regret bound of saving at most S\sqrt{S} or S16T112S^{\frac{1}{6}}T^{\frac{1}{12}}.

The paper proves geometric and spectral alignment for deep neural networks.

problem Understanding the singular spectra of deep neural network layers.
method Proves deterministic quotient-geometric estimates for singular spectra of Frobenius-normalized layer factors.
result Exact power-law spectra form a trace-normalized Cartan orbit under Frobenius normalization.

A new framework maximizes influence spread in social networks by accounting for inter-community diffusion.

problem Real-world social networks have inter-community influence that is often overlooked in community-based IM approaches.
method Community-IM++ uses a heuristic based on community-based diffusion degree and progressive budgeting to model and prioritize cross-community diffusion.
result Community-IM++ achieves near-greedy influence spread at up to 100 times lower runtime than existing methods.

Efficiently poisons offline RLHF models by flipping preference labels.

problem Vulnerability of offline RLHF models to preference label flipping attacks.
method Developed two attack methods: BAL-A and BMP-A, solving a structured binary sparse approximation problem.
result Demonstrated that flipping one preference label induces a parameter-independent shift in the DPO gradient, enabling structured binary sparse approximation.