
-
Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap
This paper presents a new model-free algorithm for episodic finite-horiz...
read it
-
Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature
This paper studies model-based bandit and reinforcement learning (RL) wi...
read it
-
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness
Consider a prediction setting where a few inputs (e.g., satellite images...
read it
-
Meta-learning Transferable Representations with a Single Target Domain
Recent works found that fine-tuning and joint training—two popular appro...
read it
-
Beyond Lazy Training for Over-parameterized Tensor Decomposition
Over-parametrization is an important technique in training neural networ...
read it
-
Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling
Document-level relation extraction (RE) poses new challenges compared to...
read it
-
Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
Self-training algorithms, which train a model to fit pseudolabels predic...
read it
-
Entity and Evidence Guided Relation Extraction for DocRED
Document-level relation extraction is a challenging task which requires ...
read it
-
Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK
We consider the dynamic of gradient descent for learning a two-layer neu...
read it
-
Simplifying Models with Unlabeled Output Data
We focus on prediction problems with high-dimensional outputs that are s...
read it
-
Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization
Real-world large-scale datasets are heteroskedastic and imbalanced – lab...
read it
-
Active Online Domain Adaptation
Online machine learning systems need to adapt to domain shifts. Meanwhil...
read it
-
Individual Calibration with Randomized Forecasting
Machine learning applications often require calibrated predictions, e.g....
read it
-
Self-training Avoids Using Spurious Features Under Domain Shift
In unsupervised domain adaptation, existing theory focuses on situations...
read it
-
Federated Accelerated Stochastic Gradient Descent
We propose Federated Accelerated Stochastic Gradient Descent (FedAc), a ...
read it
-
Model-based Adversarial Meta-Reinforcement Learning
Meta-reinforcement learning (meta-RL) aims to learn from multiple traini...
read it
-
Shape Matters: Understanding the Implicit Bias of the Noise Covariance
The noise in stochastic gradient descent (SGD) provides a crucial implic...
read it
-
MOPO: Model-based Offline Policy Optimization
Offline reinforcement learning (RL) refers to the problem of learning po...
read it
-
Robust and On-the-fly Dataset Denoising for Image Classification
Memorization in over-parameterized neural networks could severely hurt g...
read it
-
Optimal Regularization Can Mitigate Double Descent
Recent empirical and theoretical studies have shown that many learning a...
read it
-
The Implicit and Explicit Regularization Effects of Dropout
Dropout is a widely-used regularization technique, often required to obt...
read it
-
Understanding Self-Training for Gradual Domain Adaptation
Machine learning systems must adapt to data distributions that evolve ov...
read it
-
Variable-Viewpoint Representations for 3D Object Recognition
For the problem of 3D object recognition, researchers using deep learnin...
read it
-
Bootstrapping the Expressivity with Model-based Planning
We compare the model-free reinforcement learning with the model-based ap...
read it
-
Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin
For linear classifiers, the relationship between (normalized) output mar...
read it
-
Verified Uncertainty Calibration
Applications such as weather forecasting and personalized medicine deman...
read it
-
Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling
Imitation learning, followed by reinforcement learning algorithms, is a ...
read it
-
A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning
The aim of multi-task reinforcement learning is two-fold: (1) efficientl...
read it
-
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks
Stochastic gradient descent with a large initial learning rate is a wide...
read it
-
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
Deep learning algorithms can fare poorly when the training dataset suffe...
read it
-
On the Performance of Thompson Sampling on Logistic Bandits
We study the logistic bandit, in which rewards are binary with success p...
read it
-
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation
Existing Rademacher complexity bounds for neural networks rely only on n...
read it
-
Fixup Initialization: Residual Learning Without Normalization
Normalization layers are a staple in state-of-the-art deep neural networ...
read it
-
On the Margin Theory of Feedforward Neural Networks
Past works have shown that, somewhat surprisingly, over-parametrization ...
read it
-
Algorithmic Framework for Model-based Reinforcement Learning with Theoretical Guarantees
While model-based reinforcement learning has empirically been shown to s...
read it
-
Approximability of Discriminators Implies Diversity in GANs
While Generative Adversarial Networks (GANs) have empirically produced i...
read it
-
Seeing Neural Networks Through a Box of Toys: The Toybox Dataset of Visual Object Transformations
Deep convolutional neural networks (CNNs) have enjoyed tremendous succes...
read it
-
Optimal Design of Process Flexibility for General Production Systems
Process flexibility is widely adopted as an effective strategy for respo...
read it
-
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors
Motivations like domain adaptation, transfer learning, and feature learn...
read it
-
Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations
We show that the (stochastic) gradient descent algorithm provides an imp...
read it
-
Algorithmic Regularization in Over-parameterized Matrix Recovery
We study the problem of recovering a low-rank matrix X^ from linear meas...
read it
-
Learning One-hidden-layer Neural Networks with Landscape Design
We consider the problem of learning a one-hidden-layer neural network: w...
read it
-
On the Optimization Landscape of Tensor Decompositions
Non-convex optimization with local search heuristics has been widely use...
read it
-
Generalization and Equilibrium in Generative Adversarial Nets (GANs)
We show that training of generative adversarial network (GAN) may not ha...
read it
-
Provable learning of Noisy-or Networks
Many machine learning applications use latent variable models to explain...
read it
-
Identity Matters in Deep Learning
An emerging design principle in deep learning is that each layer of a de...
read it
-
Finding Approximate Local Minima Faster than Gradient Descent
We design a non-convex second-order optimization algorithm that is guara...
read it
-
A Non-generative Framework and Convex Relaxations for Unsupervised Learning
We give a novel formal theoretical framework for unsupervised learning w...
read it
-
Gradient Descent Learns Linear Dynamical Systems
We prove that gradient descent efficiently converges to the global optim...
read it
-
Provable Algorithms for Inference in Topic Models
Recently, there has been considerable progress on designing algorithms w...
read it