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.

168,742 papers · 148 categories

Trend · papers per month

4896143191 · Jun 202019922001200920172026
48 results for tuning curves

Confidence bands for tuning curves improve hyperparameter comparison in NLP.

problem Ambiguity in comparing hyperparameter tuning methods.
method Constructs exact, simultaneous, and distribution-free confidence bands for tuning curves.
result Confidence bands provide a robust basis for comparing methods rigorously.

Improved neural population modeling using shared features and ensemble detection.

problem Missing shared coding properties in neural latent variable models.
method Feature sharing across tuning curves and soft clustering of neurons.
result More interpretable and better-performing neural population models.

HAMLET optimizes algorithm selection for machine learning tasks.

problem Limited time budgets and computational resources make traditional bandit approaches ineffective for automated algorithm selection.
method HAMLET incorporates learning curve extrapolation and time-awareness to select machine learning algorithms.
result HAMLET variants outperform other bandit-based strategies in experiments with recorded hyperparameter tuning traces.

LoRA-Curve connects independent LoRA optima through continuous low-loss valleys, improving Bayesian model averaging.

problem Challenges in estimating epistemic uncertainty in LoRA-based Bayesian inference.
method Introduces LoRA-Curve, a segmented Bézier curve parameterization in the LoRA space, with free and anchored configurations.
result Empirically shows that connecting independent LoRA optima through continuous low-loss valleys improves mutual information of the predictive distribution.

Study of closed real plane curves with hyperelliptic genus three solutions.

problem Analyzing real plane curves with specific curvature equations.
method Examined real plane curves associated with the focusing gauged modified KdV equation of genus three.
result Showed closed real plane curves beyond Euler's figure-eight elastica.

Paper fine-tunes LLaMA-3-8B for financial NER using instruction and LoRA.

problem LLMs struggle with financial NER, especially differentiating entities and amounts.
method Instruction fine-tuning combined with LoRA for parameter-efficient learning.
result Micro-F1 score of 0.894 on financial NER tasks, outperforming other models.

In this paper, we consider the discrete deformation of the discrete space curves with constant torsion described by the discrete mKdV or the discrete sine-Gordon equations, and show that it is formulated as the torsion-preserving equidistant deformation on the osculating plane which satisfies the isoperimetric conditio…

2013-11-18abs ↗pdf ↗

We formalize AURC and develop estimators for SC systems.

problem Evaluation of SC systems' performance.
method Formal statistical formulation, Monte Carlo methods, plug-in estimators.
result Plug-in estimators are consistent, with low bias and bounded MSE.

New metric captures individual neuron tuning across neural networks.

problem Need a metric that respects individual neuron tuning across different neural networks.
method Derived a 'soft' permutation-based metric using optimal transport theory.
result Metric avoids counter-intuitive outcomes and captures geometric insights.

New model predicts neural network performance from early training epochs, incorporating architecture impact.

problem Predicting neural network performance from early training epochs, neglecting architecture impact.
method Architecture-aware graph ordinary differential equation model.
result Model outperforms state-of-the-art methods for MLP and CNN learning curves.

Single training run learns optimal VAE parameters for various β values.

problem Training VAEs with varying β values for optimal trade-off between distortion and rate.
method Introduced Multi-Rate VAE (MR-VAE) using hypernetworks to map β to optimal parameters.
result MR-VAEs can construct the full rate-distortion curve without additional training.

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.

Detects potential depegs in Curve's StableSwap pools to protect LPs.

problem Detecting and alerting LPs to potential depegs in Curve's StableSwap pools.
method Constructed metrics based on price and trading data, fine-tuned BOCD algorithm.
result Model detects USDC depeg 5 hours before price dip, with few false alarms.

Study reveals learning curves and benign overfitting in spectral algorithms for large dimensions.

problem Understanding learning curves and benign overfitting in spectral algorithms for large-dimensional data.
method Analysis of learning curves and benign overfitting in spectral algorithms for inner-product kernels on the sphere and general domains.
result Characterization of three distinct regimes: over-regularized, under-regularized, and interpolation regimes, revealing benign overfitting across both under-regularized and interpolation regimes.

Algorithm allocates budgets to tasks with semi-bandit feedback, achieving near-optimal regret bounds.

problem Stochastic budget allocation with censored semi-bandit feedback.
method Optimism-based algorithm operating under censored semi-bandit feedback.
result Regret scales polylogarithmically with horizon T in diminishing-returns regimes.

Echo State Networks (ESNs) are recurrent neural networks that only train their output layer, thereby precluding the need to backpropagate gradients through time, which leads to significant computational gains. Nevertheless, a common issue in ESNs is determining its hyperparameters, which are crucial in instantiating a …

2019-03-12abs ↗pdf ↗

We investigate a long-debated question, which is how to create predictive models of recidivism that are sufficiently accurate, transparent, and interpretable to use for decision-making. This question is complicated as these models are used to support different decisions, from sentencing, to determining release on proba…

2015-03-26abs ↗pdf ↗

Automates fitting semiconductor device models using approximate Bayesian computation.

problem Manual tuning of parameters for fitting TFT models to experimental data is inefficient and prone to errors.
method Approximate Bayesian Computation (aBc) for generating posterior distributions of estimated parameters.
result The proposed method accurately predicts model parameters from mobility curves using gradient boosted trees.

Partial dependence curves (FPD) introduced by Friedman, are an important model interpretation tool, but are often not accessible to business analysts and scientists who typically lack the skills to choose, tune, and assess machine learning models. It is also common for the same partial dependence algorithm on the same …

2019-07-15abs ↗pdf ↗

We introduce GAMSEL (Generalized Additive Model Selection), a penalized likelihood approach for fitting sparse generalized additive models in high dimension. Our method interpolates between null, linear and additive models by allowing the effect of each variable to be estimated as being either zero, linear, or a low-co…

2015-06-11abs ↗pdf ↗

New method reduces fine-tuning cost for reused models.

problem Repeating fine-tuning costs with outdated foundation models.
method Portable Reward Tuning (PRT) trains a reward model to maximize the same loss function as fine-tuning.
result PRT achieves comparable accuracy to inference-time tuning with less inference cost.

New method adapts neural networks without losing prior knowledge.

problem Understanding and enabling flexible adaptation of neural networks.
method Differential geometry framework, functionally invariant paths (FIP).
result Achieves comparable state-of-the-art performance on continual learning and sparsification tasks.

Learning shrinks hard tail, improving inference performance.

problem Improving inference performance in neural networks.
method Latent Instance Difficulty (LID) model analyzing fine-tuning of neural networks.
result Training-dependent inference scaling, with βexteffβ_ ext{eff} growing with sample size before saturating.

New method quantifies uncertainty in fine-tuned LLMs using LoRA ensembles.

problem Uncertainty in fine-tuned LLMs and how to trust their predictions.
method Posterior approximations using low-rank adaptation ensembles.
result Unexpected retention of acquired knowledge during fine-tuning in overfitting regime.

BERT fine-tuning is unstable due to optimization issues, not forgetting or dataset size.

problem Stability of fine-tuning BERT-based models across different random seeds.
method Analysis of BERT, RoBERTa, and ALBERT fine-tuned on GLUE datasets, identifying optimization difficulties as the cause of instability.
result Fine-tuning instability is due to optimization difficulties leading to vanishing gradients, not forgetting or dataset size.

ADAPT improves robustness of Vision Transformers without full model fine-tuning.

problem Vulnerability of Vision Transformers to adversarial attacks.
method Parameter-efficient prompt tuning with ADAPT framework for adaptive adversarial training.
result ADAPT achieves robust accuracy of ~40% w.r.t. SOTA methods using only ~1% of the parameters.

Paper proposes a reinforcement learning framework for efficient hyper-parameter tuning of stochastic optimization algorithms.

problem Efficient tuning of hyper-parameters for stochastic optimization algorithms.
method Modeling hyper-parameter tuning as a Markov decision process and using policy gradient algorithms.
result The proposed framework significantly reduces the time required for hyper-parameter tuning compared to Bayesian optimization.

Improved code translation by preserving structure with composed fine-tuning.

problem Improving code translation accuracy with unlabeled code outputs.
method Pre-trained denoiser to capture output structure, composed fine-tuning to fine-tune predictor.
result Composed fine-tuning significantly improves generalization over standard fine-tuning.

The paper introduces a Hessian-based method to improve generalization in fine-tuned deep neural networks.

problem Improving generalization in fine-tuned deep neural networks, especially in noisy conditions.
method PAC-Bayesian analysis to identify a Hessian-based distance measure, proving generalization bounds, and developing an algorithm with a generalization error guarantee.
result Hessian-based distance measure correlates well with observed generalization gaps and can match the scale of these gaps in practice.

A new robust prefix-tuning framework improves model robustness against adversarial attacks.

problem Lack of robustness in prefix-tuning for adversarial attacks.
method Leveraging layerwise activations of pretrained models for additional prefix finetuning during the test phase.
result Framework substantially improves robustness over strong baselines while maintaining comparable accuracy on clean texts.

Optimizes sparse fine-tuning for privacy in neural networks.

problem Performance gap between DP-SGD and non-private fine-tuning.
method Optimization-based approach using private gradient information for selecting trainable weights.
result Our selection method leads to better prediction accuracy compared to existing approaches.

Single-head transformers with a single self-attention layer can approximate any sequence-to-sequence function and are efficient under certain conditions.

problem Statistical and computational limits of prompt tuning for transformer-based models.
method Investigation of single-head transformers with a single self-attention layer, proving universality and efficiency under SETH.
result Existence of almost-linear time prompt tuning inference algorithms under certain conditions.

Mango automates hyperparameter tuning for large-scale ML training.

problem Manual hyperparameter tuning is tedious and inefficient for large-scale machine learning.
method Parallel hyperparameter tuning with intelligent search strategies and flexible abstractions.
result Mango achieves comparable performance to Hyperopt while supporting distributed computing.

Fine-tuning harms in-context learning, but restricting updates to the value matrix improves zero-shot performance.

problem Fine-tuning harms in-context learning, reducing zero-shot performance on unseen tasks.
method Theoretical analysis of linear attention models, identifying conditions for degraded few-shot performance.
result Restricting updates to the value matrix improves zero-shot performance while preserving in-context learning.