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

2468 · Feb 202419922001200920172026
48 results for weak-to-strong finetuning

W2S FT often outperforms weak teachers due to low intrinsic dimensionality.

problem Understanding why weak-to-strong finetuning outperforms weak models.
method Analyzing W2S in ridgeless regression setting, focusing on variance reduction.
result Weak teacher's variance is inherited by strong student in shared feature subspace, reduced in discrepancy subspace.

RAVEN improves weak-to-strong generalization under distribution shifts.

problem Weak models fail to supervise strong models effectively under distribution shifts.
method RAVEN dynamically learns optimal combinations of weak models and strong model parameters.
result RAVEN outperforms existing methods by over 30% on out-of-distribution tasks.

Paper analyzes weak-to-strong generalization in CNNs, identifying data-scarce and data-abundant regimes.

problem Weak-to-strong generalization in CNNs trained on weak models.
method Formal analysis of gradient descent dynamics in data-scarce and data-abundant regimes.
result Identifies two regimes and distinct mechanisms of generalization in each.

New model shows weak teachers can help strong students learn even with imperfect labels.

problem Improving strong student's performance with weak teacher's imperfect pseudolabels.
method Stylized overparameterized spiked covariance model with Gaussian covariates, proving two phases of generalization.
result Provable successful and random guessing phases of strong student's generalization.

Random feature models can outperform a weak teacher with early stopping.

problem Generalization from a weak to a strong model in random feature networks.
method Random feature models, early stopping, proving weak-to-strong generalization.
result Random feature models can outperform a weak teacher with early stopping.

The paper reveals three mechanisms for weak-to-strong generalization.

problem Understanding the mechanisms behind weak-to-strong generalization in imperfect labeling scenarios.
method Theoretical analysis of simple models including ridge regression and weighted ridge regression, and a nonlinear multi-index setting.
result A student model can compensate for a teacher's under-regularization and achieve lower test error.

The study explores the strengths and weaknesses of models that generalize from weak to strong supervision.

problem Understanding the limitations and capabilities of models that generalize from weak to strong supervision.
method Theoretical analysis and experimental validation in both classification and regression settings.
result Theoretical bounds reveal the importance of strong generalization and calibration of the weak model and a careful balance in the training process.

Improved machine learning models outperform their simpler counterparts by using imperfect labels.

problem Improving model performance using imperfect labels.
method Random feature ridge regression (RFRR) with a deterministic equivalent for excess test error.
result The student model can outperform the teacher model regardless of the teacher's scaling law, achieving the minimax optimal rate.

Study shows how a strong model can learn a task's feature while retaining other capabilities.

problem How to align superhuman AI systems using weak-to-strong generalization.
method Two-layer neural networks, reward-model learning, multi-step SGD, feature learning.
result The strong model efficiently learns task features while retaining general capabilities.

Boosting is a popular way to derive powerful learners from simpler hypothesis classes. Following previous work (Mason et al., 1999; Friedman, 2000) on general boosting frameworks, we analyze gradient-based descent algorithms for boosting with respect to any convex objective and introduce a new measure of weak learner p…

2011-05-10abs ↗pdf ↗

Unified finetuning of all quantization degrees of freedom achieves state-of-the-art 4-bit quantization.

problem Achieving high accuracy in quantized neural networks while maintaining speed and resource constraints.
method Quantization-aware finetuning (QFT) that jointly optimizes all quantization degrees of freedom.
result 4-bit weight quantization results on-par with state-of-the-art (SoTA) within PTQ constraints.

New research shows label refinement and weak training have limitations for aligning LLMs.

problem Limitations of refinement methods for aligning large language models.
method Analyzed probabilistic assumptions and alternative approaches to label refinement and weak training.
result Label refinement and weak training suffer from irreducible error, leaving a performance gap.

Study shows pretraining and finetuning can effectively tackle covariate shift in linear regression.

problem Linear regression under covariate shift where source and target distributions differ but conditional distribution remains similar.
method Pretraining on source data and finetuning on target data using online SGD.
result Transfer learning with O(N2)O(N^2) source data is as effective as supervised learning with NN target data.

LoRAs enable efficient adaptation of large models; this paper explores processing LoRA weights with machine learning.

problem Efficient processing of low-rank weight decompositions in large finetuned models.
method Developed symmetry-aware invariant and equivariant LoL models to process LoRA weights.
result LoL models can predict CLIP scores, finetuning data attributes, and accuracy on downstream tasks.

This paper bridges offline and online RL by studying policy finetuning with a reference policy.

problem Sample-efficient reinforcement learning in online and offline settings.
method Design of policy finetuning algorithms and analysis of sample complexity.
result Theoretical analysis shows that the optimal policy finetuning algorithm is either offline reduction or purely online RL.

Vanishing gradients hinder reinforcement finetuning of language models.

problem Vanishing gradients impede the optimization of language models using reinforcement finetuning.
method The study identifies vanishing gradients as a fundamental optimization obstacle in reinforcement finetuning and proposes an initial supervised finetuning phase to mitigate this issue.
result An initial supervised finetuning phase is crucial for successful reinforcement finetuning of language models, as it helps prevent vanishing gradients and maximizes rewards.

New framework reduces LLM complexity by directly finetuning in Boolean domain.

problem Reducing the complexity of large language models (LLMs) while maintaining performance.
method Proposes a novel framework using multi-kernel Boolean parameters for direct finetuning in the Boolean domain.
result Significantly reduces complexity during both finetuning and inference, outperforming recent techniques.

Meta-learning techniques like MAML and Reptile fail to generalize well to out-of-distribution tasks compared to simple finetuning.

problem Generalization of meta-learning techniques in low-data scenarios.
method Investigation of MAML, Reptile, and finetuning on various tasks.
result MAML and Reptile specialize for fast adaptation but fail to generalize to out-of-distribution tasks.

ConMeZO speeds up zeroth-order optimization for large language models.

problem Slow convergence in high-dimensional parameter spaces of large language models.
method Adaptive directional sampling in a cone centered around a momentum estimate.
result Achieves the same convergence rate as MeZO but up to 2X faster.

Vision transformers benefit from non-smooth components in adaptation.

problem Understanding the role of non-smoothness in vision transformer adaptation.
method Theoretical analysis and extensive experiments on large-scale vision transformers.
result High plasticity of attention modules and feedforward layers leads to better finetuning performance.

Paper introduces RiskEmbed, a finetuned model for financial risk management.

problem Improving retrieval accuracy in financial question-answering systems.
method Curated dataset and finetuned BERT model for financial domain.
result RiskEmbed significantly outperforms general-purpose and financial embedding models.

BioFinBERT analyzes sentiment of biotech press releases and financial text around inflection points.

problem Analyzing sentiment of biotech press releases and financial text around inflection points.
method Finetuning BioBERT on financial datasets to create BioFinBERT for sentiment analysis.
result BioFinBERT accurately analyzes sentiment of biotech press releases and financial text around inflection points.

Boosting weak learners to strong ones from aggregate labels is possible for LLP but not for MIL.

problem Boosting weak learners to strong ones from aggregate labels in learning from label proportions (LLP).
method Using a weak learner on large enough bags to obtain a strong learner for small bags in polynomial time.
result Boosting is possible for LLP but not for MIL.

Sharp analysis of knowledge distillation for high-dimensional regression.

problem Characterizing the risk of target models in high-dimensional settings.
method Sharp non-asymptotic bounds for ridgeless regression under model and distribution shifts.
result Identifies optimal surrogate models and reveals benefits and limitations of discarding weak features.

Study on W2S generalization with spurious correlations, proposing remedies.

problem Understanding and improving W2S generalization with spurious correlations.
method Theoretical analysis and algorithmic remedies for W2S fine-tuning.
result W2S always happens with sufficient pseudolabels when group fractions match, but may fail otherwise.

WebGUM learns web navigation from multimodal data, outperforming previous methods.

problem Limited generalization from domain-specific models in web navigation.
method Instruction-following multimodal agent trained on vision-language foundation models.
result Significant improvement in web navigation performance on benchmarks.

Improves retrieval accuracy for hierarchical documents, especially for distant matches.

problem Limited expressive power of dual encoder models in hierarchical retrieval.
method Proves feasibility of DEs for HR, introduces pretrain-finetune recipe to improve long-distance retrieval.
result Pretrain-finetune boosts recall on long-distance pairs from 19% to 76%.

Study improves cryptocurrency price prediction using unlabeled text data.

problem Predicting cryptocurrency returns from unlabelled text data.
method Introduced weak learning approach to finetune BERT on unlabeled text data.
result Finetuning pretrained NLP models with weak labels enhances forecast accuracy.

MPP trains a transformer to predict multiple physical systems, improving accuracy across various tasks.

problem Training models for specific physical systems is inefficient and requires fine-tuning.
method MPP trains a shared transformer on multiple heterogeneous physical systems, projecting fields into a shared embedding space.
result A single MPP-pretrained transformer outperforms task-specific models on all pretraining sub-tasks and downstream tasks.

This dissertation automates deep learning pipelines and uses meta-learning for better model selection and data augmentation.

problem Challenges in selecting and fine-tuning deep learning pipelines for new datasets.
method Meta-learning for DL pipeline selection and data augmentation, using synthetic data.
result Meta-learned approaches outperform traditional methods in automated DL pipeline selection and data augmentation.

Proposes a new algorithm for efficient online model selection of LLMs considering the increasing-then-converging trend.

problem Balancing cost and performance in choosing the best LLM among a diverse set of models.
method Introduces a time-increasing bandit algorithm (TI-UCB) that predicts model performance increases and balances exploration and exploitation.
result Achieves a logarithmic regret upper bound, indicating a fast convergence rate in model selection.