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.

168,657 papers · 148 categories

Trend · papers per month

3857711,1561,541 · Jun 202019922001200920172026
48 results for student-teacher learning

Student-teacher learning improves generalization with noisy inputs.

problem Transfer knowledge from clean inputs to noisy inputs.
method Analyzes student-teacher learning using deep linear networks and experiments with nonlinear networks.
result Three factors are vital for success: zero training loss, teacher knowledge, and feature decomposition.

This work proposes a student-teacher network for predicting hospital admission locations.

problem Accurate prediction of hospital admission locations to optimize resource allocation.
method Reinforcement learning approach where a teacher network selects data batches for a student network.
result The approach outperforms state-of-the-art methods on tabular data and image recognition.

KD can lead to student-teacher deviations that improve performance.

problem KD can lead to student-teacher deviations that may outperform the teacher.
method Characterized and explained the nature of student-teacher deviations through experiments and theory.
result KD can lead to improved generalization by exaggerating the implicit bias of gradient descent.

LoRA fine-tuning explained with gradient dynamics for low-rank perturbations.

problem Understanding why gradient descent converges to useful low-rank perturbations in LoRA fine-tuning.
method Generalized student-teacher setting with i.i.d. samples and online gradient descent.
result Gradient descent converges to the teacher model in dkO(1)dk^{O(1)} iterations under certain conditions.

Study shows RFRR's effectiveness with nearly orthogonal data in overparameterized settings.

problem Understanding the effectiveness of random feature regression with nearly orthogonal data.
method Investigates RFRR with nearly orthogonal deterministic unit-length input data vectors in the overparameterized regime.
result Shows high-probability non-asymptotic concentration results for RFRR's training, cross-validation, and generalization errors.

This is a report of our lessons learned building acoustic models from 1 Million hours of unlabeled speech, while labeled speech is restricted to 7,000 hours. We employ student/teacher training on unlabeled data, helping scale out target generation in comparison to confidence model based methods, which require a decoder…

2019-04-02abs ↗pdf ↗

Large scale machine learning (ML) systems such as the Alexa automatic speech recognition (ASR) system continue to improve with increasing amounts of manually transcribed training data. Instead of scaling manual transcription to impractical levels, we utilize semi-supervised learning (SSL) to learn acoustic models (AM) …

2019-04-24abs ↗pdf ↗

Lifelong learning is the problem of learning multiple consecutive tasks in a sequential manner, where knowledge gained from previous tasks is retained and used to aid future learning over the lifetime of the learner. It is essential towards the development of intelligent machines that can adapt to their surroundings. I…

2017-05-27abs ↗pdf ↗

Study analyzes learning dynamics in nonlinear perceptrons using stochastic-process approach.

problem Understanding the roles of nonlinearity and input-data distribution in neural network learning.
method Stochastic-process approach to derive flow equations for learning dynamics in nonlinear perceptrons.
result Input-data noise affects learning speed differently under supervised and reinforcement learning.

A new gradient flow for MMD with closed-form implementation.

problem Existing gradient flows either lack tractable numerical implementation or require strong assumptions.
method Introduces a (de)-regularized Maximum Mean Discrepancy (DrMMD) and its gradient flow.
result Guarantees near-global convergence for a broad class of targets in both continuous and discrete time.

This work analyzes neural scaling laws using power-law data spectra and derives analytical expressions for generalization error.

problem Understanding how neural network performance scales with key factors like data size and model complexity.
method Statistical mechanics techniques applied to one-pass stochastic gradient descent in a student-teacher framework.
result Derivation of analytical expressions for generalization error under power-law data spectra and identification of conditions for power-law scaling.

One gradient step improves neural network feature learning by aligning weights with the teacher model.

problem Improving feature learning in neural networks through gradient descent.
method First gradient descent step on the first-layer parameters of a two-layer neural network.
result The first gradient update contains a rank-1 spike, leading to alignment with the teacher model.

Grokking occurs when neural networks transition from lazy to rich training dynamics, fitting initial features before generalizing.

problem Understanding why neural networks exhibit early train loss decrease without corresponding test loss improvement.
method Analyzing vanilla gradient descent on polynomial regression with a two-layer neural network, identifying sufficient statistics for test loss.
result Grokking arises when a network first attempts to fit a kernel regression solution with initial features, followed by late-time feature learning.

One-pass SGD dynamics in overparameterized quadratic networks show slow escape from poor solutions.

problem Slow escape from poor generalization solutions in overparameterized neural networks.
method Analysis of one-pass SGD dynamics using ordinary differential equations for overlap matrices.
result Overparameterization only modestly accelerates escape from poor solutions.

PETAL adapts models to changing target domains over time.

problem Lifelong test-time adaptation in changing target domains.
method Probabilistic framework with student-teacher model and data-driven parameter restoration.
result PETAL achieves better results than state-of-the-art for online lifelong test-time adaptation.

Meta-learning improves neural networks by adapting learning algorithms.

problem Conventional AI approaches solve tasks from scratch, but meta-learning aims to improve the learning algorithm.
method Meta-learning adapts a learning algorithm based on multiple learning episodes.
result Meta-learning can tackle deep learning challenges like data and computation bottlenecks.

Study Whittle index learning algorithms for restless bandits with constant stepsizes.

problem Optimizing decisions in restless multi-armed bandits with constant stepsizes.
method Developed Q-learning algorithms with constant stepsizes for index learning in restless bandits, extending to DQN and function approximations.
result The algorithms learn the Whittle index effectively.

New unsupervised learning technique learns independent kernels for better machine learning tasks.

problem Improving unsupervised representation learning for machine learning tasks.
method Stacking convolutional transforms using alternating proximal minimization scheme.
result DCTL outperforms shallow version CTL on benchmark datasets.

New self-imitation learning method improves performance in continuous control tasks.

problem Improving off-policy learning in continuous control tasks.
method Proposes a n-step lower bound to generalize lower-bound Q-learning and introduces a new family of self-imitation learning algorithms.
result n-step lower bound Q-learning achieves a better trade-off between bias and contraction rate, leading to improved performance.

Deep reinforcement learning finds optimal learning policies for adaptive systems.

problem Finding individualized learning plans for learners with unknown latent traits.
method Formulated as a Markov decision process, applied deep Q-learning with a transition model estimator.
result The algorithm efficiently discovers optimal learning policies with small data sets.

Study batch reinforcement learning methods for personalized medical treatments.

problem Batch reinforcement learning for personalized medical treatments.
method Direct policy learning and model-based learning approaches.
result Model-based learning is impossible with finite model classes but feasible with relaxed conditions.

A new meta-meta classification method tackles few-shot learning tasks.

problem Learning with limited data in small-data settings.
method Designing an ensemble of learners for a large set of problems, then learning how to combine them for a new problem.
result Meta-meta classification outperforms traditional meta-learning and ensembling approaches in one-shot learning tasks.

Paper analyzes iterative learning for concept classes and learns half-spaces.

problem Learning concept classes efficiently with iterative learners.
method Analyzes various settings of iterative learning and provides a constructive algorithm for half-spaces.
result Constructive iterative algorithm for learning half-spaces from informant.