Search Results for author:
Found 43 papers, 3 papers with code
Gradient Guidance for Diffusion Models: An Optimization Perspective
To remedy this issue, we consider a modified form of gradient guidance based on a forward prediction loss, which leverages the pre-trained score function to preserve the latent structure in generated samples.
An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
In this paper, we review emerging applications of diffusion models, understanding their sample generation under various controls.
Diffusion Model for Data-Driven Black-Box Optimization
In this paper, we focus on diffusion models, a powerful generative AI technology, and investigate their potential for black-box optimization over complex structured variables.
Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning.
Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models
Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties.
Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks
In fact, human preference data are now used with classic reinforcement learning algorithms such as actor-critic methods, which involve evaluating an intermediate policy over a reward learned from human preference data with distribution shift, known as off-policy evaluation (OPE).
Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds
As a result, by properly choosing the network size and hyperparameters, NPMD can find an $\epsilon$-optimal policy with $\widetilde{O}(\epsilon^{-\frac{d}{\alpha}-2})$ samples in expectation, where $\alpha\in(0, 1]$ indicates the smoothness of environment.
Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems
A popular approach is to utilize human feedback to learn a reward function for training.
Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight
This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case.
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
Convolutional residual neural networks (ConvResNets), though overparameterized, can achieve remarkable prediction performance in practice, which cannot be well explained by conventional wisdom.
Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories
Existing theories on deep nonparametric regression have shown that when the input data lie on a low-dimensional manifold, deep neural networks can adapt to the intrinsic data structures.
Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations
We present algorithms and establish near-optimal regret upper and lower bounds, of the form $\tilde{\mathcal{O}}(\sqrt{{\rm poly}(H) SAK})$, for RL in the delayed and missing observation settings.
Counterfactual Generative Models for Time-Varying Treatments
Estimating the counterfactual outcome of treatment is essential for decision-making in public health and clinical science, among others.
AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
Therefore, many fine-tuning methods are proposed to learn incremental updates of pre-trained weights in a parameter efficient way, e. g., low-rank increments.
On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds
Many existing experiments have demonstrated that generative networks can generate high-dimensional complex data from a low-dimensional easy-to-sample distribution.
Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data
Furthermore, the generated distribution based on the estimated score function captures the data geometric structures and converges to a close vicinity of the data distribution.
High Dimensional Binary Classification under Label Shift: Phase Transition and Regularization
Label Shift has been widely believed to be harmful to the generalization performance of machine learning models.
Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint
Overparameterized neural networks enjoy great representation power on complex data, and more importantly yield sufficiently smooth output, which is crucial to their generalization and robustness.
Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks
We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks.
A Manifold Two-Sample Test Study: Integral Probability Metric with Neural Networks
Based on the approximation theory of neural networks, we show that the neural network IPM test has the type-II risk in the order of $n^{-(s+\beta)/d}$, which is in the same order of the type-II risk as the H\"older IPM test.
Deep Learning Assisted End-to-End Synthesis of mm-Wave Passive Networks with 3D EM Structures: A Study on A Transformer-Based Matching Network
This paper presents a deep learning assisted synthesis approach for direct end-to-end generation of RF/mm-wave passive matching network with 3D EM structures.
Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces
Learning operators between infinitely dimensional spaces is an important learning task arising in wide applications in machine learning, imaging science, mathematical modeling and simulations, etc.
Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL
Theoretically, under a weak coverage assumption that the experience dataset contains enough information about the optimal policy, we prove that for an episodic mean-field MDP with a horizon $H$ and $N$ training trajectories, SAFARI attains a sub-optimality gap of $\mathcal{O}(H^2d_{\rm eff} /\sqrt{N})$, where $d_{\rm eff}$ is the effective dimension of the function class for parameterizing the value function, but independent on the number of agents.
Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect
Moreover, we rigorously establish an implicit bias of GD induced by such a large learning rate, termed 'balancing', meaning that magnitudes of $X$ and $Y$ at the limit of GD iterations will be close even if their initialization is significantly unbalanced.
Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks
Most of existing statistical theories on deep neural networks have sample complexities cursed by the data dimension and therefore cannot well explain the empirical success of deep learning on high-dimensional data.
Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization
The Lottery Ticket Hypothesis suggests that an over-parametrized network consists of ``lottery tickets'', and training a certain collection of them (i. e., a subnetwork) can match the performance of the full model.
Differentiable Top-k with Optimal Transport
Finding the k largest or smallest elements from a collection of scores, i. e., top-k operation, is an important model component widely used in information retrieval, machine learning, and data mining.
Doubly Robust Off-Policy Learning on Low-Dimensional Manifolds by Deep Neural Networks
Our theory shows that deep neural networks are adaptive to the low-dimensional geometric structures of the covariates, and partially explains the success of deep learning for causal inference.
Differentiable Top-$k$ with Optimal Transport
The top-$k$ operation, i. e., finding the $k$ largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining.
How Important is the Train-Validation Split in Meta-Learning?
A common practice in meta-learning is to perform a train-validation split (\emph{train-val method}) where the prior adapts to the task on one split of the data, and the resulting predictor is evaluated on another split.
Residual Network Based Direct Synthesis of EM Structures: A Study on One-to-One Transformers
We propose using machine learning models for the direct synthesis of on-chip electromagnetic (EM) passive structures to enable rapid or even automated designs and optimizations of RF/mm-Wave circuits.
Towards Understanding Hierarchical Learning: Benefits of Neural Representations
When the trainable network is the quadratic Taylor model of a wide two-layer network, we show that neural representation can achieve improved sample complexities compared with the raw input: For learning a low-rank degree-$p$ polynomial ($p \geq 4$) in $d$ dimension, neural representation requires only $\tilde{O}(d^{\lceil p/2 \rceil})$ samples, while the best-known sample complexity upper bound for the raw input is $\tilde{O}(d^{p-1})$.
Differentiable Top-k Operator with Optimal Transport
The top-k operation, i. e., finding the k largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining.
Distribution Approximation and Statistical Estimation Guarantees of Generative Adversarial Networks
Generative Adversarial Networks (GANs) have achieved a great success in unsupervised learning.
On Computation and Generalization of Generative Adversarial Imitation Learning
Generative Adversarial Imitation Learning (GAIL) is a powerful and practical approach for learning sequential decision-making policies.
Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds
The network size scales exponentially in the approximation error, with an exponent depending on the intrinsic dimension of the data and the smoothness of the function.
On Generalization Bounds of a Family of Recurrent Neural Networks
We remark: (1) Our generalization bound for vanilla RNNs is significantly tighter than the best of existing results; (2) We are not aware of any other generalization bounds for MGU, LSTM, and Conv RNNs in the exiting literature; (3) We demonstrate the advantages of these variants in generalization.
Towards Understanding the Importance of Shortcut Connections in Residual Networks
We show, however, that gradient descent combined with proper normalization, avoids being trapped by the spurious local optimum, and converges to a global optimum in polynomial time, when the weight of the first layer is initialized at 0, and that of the second layer is initialized arbitrarily in a ball.
Nonparametric Regression on Low-Dimensional Manifolds using Deep ReLU Networks : Function Approximation and Statistical Recovery
It therefore demonstrates the adaptivity of deep ReLU networks to low-dimensional geometric structures of data, and partially explains the power of deep ReLU networks in tackling high-dimensional data with low-dimensional geometric structures.
On Scalable and Efficient Computation of Large Scale Optimal Transport
Optimal Transport (OT) naturally arises in many machine learning applications, yet the heavy computational burden limits its wide-spread uses.
On Computation and Generalization of Generative Adversarial Networks under Spectrum Control
Generative Adversarial Networks (GANs), though powerful, is hard to train.
On Computation and Generalization of GANs with Spectrum Control
Specifically, we propose a new reparameterization approach for the weight matrices of the discriminator in GANs, which allows us to directly manipulate the spectra of the weight matrices through various regularizers and constraints, without intensively computing singular value decompositions.
Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization
Specifically, our goal is to estimate the principle component of time series data with respect to the covariance matrix of the stationary distribution.
