Kenji Kawaguchi

research

∙ 07/23/2023

Tackling the Curse of Dimensionality with Physics-Informed Neural Networks

The curse-of-dimensionality (CoD) taxes computational resources heavily ...

0 Zheyuan Hu, et al. ∙

research

∙ 06/18/2023

IF2Net: Innately Forgetting-Free Networks for Continual Learning

Continual learning can incrementally absorb new concepts without interfe...

0 Depeng Li, et al. ∙

research

∙ 06/16/2023

Multi-View Class Incremental Learning

Multi-view learning (MVL) has gained great success in integrating inform...

0 Depeng Li, et al. ∙

research

∙ 06/12/2023

Fast Diffusion Model

Despite their success in real data synthesis, diffusion models (DMs) oft...

0 Zike Wu, et al. ∙

research

∙ 05/30/2023

How Does Information Bottleneck Help Deep Learning?

Numerous deep learning algorithms have been inspired by and understood v...

0 Kenji Kawaguchi, et al. ∙

research

∙ 05/28/2023

Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

Large Language Models (LLMs) have shown promising performance in knowled...

0 Minki Kang, et al. ∙

research

∙ 05/23/2023

Automatic Model Selection with Large Language Models for Reasoning

Chain-of-Thought and Program-Aided Language Models represent two distinc...

0 Xu Zhao, et al. ∙

research

∙ 05/01/2023

Decomposition Enhances Reasoning via Self-Evaluation Guided Decoding

We endow Large Language Models (LLMs) with fine-grained self-evaluation ...

0 Yuxi Xie, et al. ∙

research

∙ 04/08/2023

Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks

As machine learning has been deployed ubiquitously across applications i...

0 Yuzhen Mao, et al. ∙

research

∙ 03/01/2023

An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization

In this paper, we provide an information-theoretic perspective on Varian...

0 Ravid Shwartz-Ziv, et al. ∙

research

∙ 03/01/2023

D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory

Kohn-Sham Density Functional Theory (KS-DFT) has been traditionally solv...

0 Tianbo Li, et al. ∙

research

∙ 01/31/2023

Auxiliary Learning as an Asymmetric Bargaining Game

Auxiliary learning is an effective method for enhancing the generalizati...

0 Aviv Shamsian, et al. ∙

research

∙ 12/27/2022

MixupE: Understanding and Improving Mixup from Directional Derivative Perspective

Mixup is a popular data augmentation technique for training deep neural ...

0 Vikas Verma, et al. ∙

research

∙ 11/16/2022

Augmented Physics-Informed Neural Networks (APINNs): A gating network-based soft domain decomposition methodology

In this paper, we propose the augmented physics-informed neural network ...

0 Zheyuan Hu, et al. ∙

research

∙ 11/02/2022

Neural Active Learning on Heteroskedastic Distributions

Models that can actively seek out the best quality training data hold th...

0 Savya Khosla, et al. ∙

research

∙ 11/01/2022

Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning

Goal-conditioned reinforcement learning (RL) is a promising direction fo...

0 Riashat Islam, et al. ∙

research

∙ 10/24/2022

GFlowOut: Dropout with Generative Flow Networks

Bayesian Inference offers principled tools to tackle many critical probl...

7 Dianbo Liu, et al. ∙

research

∙ 10/15/2022

MGNNI: Multiscale Graph Neural Networks with Implicit Layers

Recently, implicit graph neural networks (GNNs) have been proposed to ca...

0 Juncheng Liu, et al. ∙

research

∙ 07/22/2022

Discrete Key-Value Bottleneck

Deep neural networks perform well on prediction and classification tasks...

4 Frederik Träuble, et al. ∙

research

∙ 06/27/2022

Robustness Implies Generalization via Data-Dependent Generalization Bounds

This paper proves that robustness implies generalization via data-depend...

0 Kenji Kawaguchi, et al. ∙

research

∙ 05/20/2022

Set-based Meta-Interpolation for Few-Task Meta-Learning

Meta-learning approaches enable machine learning systems to adapt to new...

0 Seanie Lee, et al. ∙

research

∙ 04/01/2022

Simplicial Embeddings in Self-Supervised Learning and Downstream Classification

We introduce Simplicial Embeddings (SEMs) as a way to constrain the enco...

0 Samuel Lavoie, et al. ∙

research

∙ 02/22/2022

EIGNN: Efficient Infinite-Depth Graph Neural Networks

Graph neural networks (GNNs) are widely used for modelling graph-structu...

0 Juncheng Liu, et al. ∙

research

∙ 02/02/2022

Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization

Vector Quantization (VQ) is a method for discretizing latent representat...

5 Dianbo Liu, et al. ∙

research

∙ 02/02/2022

Multi-Task Learning as a Bargaining Game

In Multi-task learning (MTL), a joint model is trained to simultaneously...

0 Aviv Navon, et al. ∙

research

∙ 01/17/2022

ExpertNet: A Symbiosis of Classification and Clustering

A widely used paradigm to improve the generalization performance of high...

0 shivin-srivastava, et al. ∙

research

∙ 01/14/2022

Training Free Graph Neural Networks for Graph Matching

We present TFGM (Training Free Graph Matching), a framework to boost the...

12 Zhiyuan Liu, et al. ∙

research

∙ 12/06/2021

Noether Networks: Meta-Learning Useful Conserved Quantities

Progress in machine learning (ML) stems from a combination of data avail...

9 Ferran Alet, et al. ∙

research

∙ 09/20/2021

When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?

Physics-informed neural networks (PINNs) have become a popular choice fo...

51 Zheyuan Hu, et al. ∙

research

∙ 07/12/2021

Meta-learning PINN loss functions

We propose a meta-learning technique for offline discovery of physics-in...

7 Apostolos F Psaros, et al. ∙

research

∙ 07/06/2021

Discrete-Valued Neural Communication

Deep learning has advanced from fully connected architectures to structu...

8 Dianbo Liu, et al. ∙

research

∙ 06/28/2021

Understanding Dynamics of Nonlinear Representation Learning and Its Application

Representations of the world environment play a crucial role in machine ...

0 Kenji Kawaguchi, et al. ∙

research

∙ 06/18/2021

Adversarial Training Helps Transfer Learning via Better Representations

Transfer learning aims to leverage models pre-trained on source data to ...

0 Zhun Deng, et al. ∙

research

∙ 06/07/2021

MemStream: Memory-Based Anomaly Detection in Multi-Aspect Streams with Concept Drift

Given a stream of entries over time in a multi-aspect data setting where...

0 Siddharth Bhatia, et al. ∙

research

∙ 05/20/2021

Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions

We propose a new type of neural networks, Kronecker neural networks (KNN...

38 Ameya D. Jagtap, et al. ∙

research

∙ 05/10/2021

Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth

Graph Neural Networks (GNNs) have been studied through the lens of expre...

0 Keyulu Xu, et al. ∙

research

∙ 04/12/2021

A Recipe for Global Convergence Guarantee in Deep Neural Networks

Existing global convergence guarantees of (stochastic) gradient descent ...

0 Kenji Kawaguchi, et al. ∙

research

∙ 02/23/2021

CAC: A Clustering Based Framework for Classification

In data containing heterogeneous subpopulations, classification performa...

0 shivin-srivastava, et al. ∙

research

∙ 02/15/2021

On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers

A deep equilibrium model uses implicit layers, which are implicitly defi...

0 Kenji Kawaguchi, et al. ∙

research

∙ 02/11/2021

When and How Mixup Improves Calibration

In many machine learning applications, it is important for the model to ...

0 Linjun Zhang, et al. ∙

research

∙ 11/09/2020

Towards Domain-Agnostic Contrastive Learning

Despite recent success, most contrastive self-supervised learning method...

0 Vikas Verma, et al. ∙

research

∙ 10/09/2020

How Does Mixup Help With Robustness and Generalization?

Mixup is a popular data augmentation technique based on taking convex co...

7 Linjun Zhang, et al. ∙

research

∙ 09/22/2020

Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time

From CNNs to attention mechanisms, encoding inductive biases into neural...

8 Ferran Alet, et al. ∙

research

∙ 09/25/2019

Locally adaptive activation functions with slope recovery term for deep and physics-informed neural networks

We propose two approaches of locally adaptive activation functions namel...

18 Ameya D. Jagtap, et al. ∙

research

∙ 08/05/2019

Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes

In this paper, we theoretically prove that gradient descent can find a g...

4 Kenji Kawaguchi, et al. ∙

research

∙ 07/09/2019

A Stochastic First-Order Method for Ordered Empirical Risk Minimization

We propose a new stochastic first-order method for empirical risk minimi...

5 Kenji Kawaguchi, et al. ∙

research

∙ 04/07/2019

Every Local Minimum is a Global Minimum of an Induced Model

For non-convex optimization in machine learning, this paper proves that ...

16 Kenji Kawaguchi, et al. ∙

research

∙ 01/12/2019

Eliminating all bad Local Minima from Loss Landscapes without even adding an Extra Unit

Recent work has noted that all bad local minima can be removed from neur...

0 Jascha Sohl-Dickstein, et al. ∙

research

∙ 01/02/2019

Elimination of All Bad Local Minima in Deep Learning

In this paper, we theoretically prove that we can eliminate all suboptim...

0 Kenji Kawaguchi, et al. ∙

research

∙ 11/20/2018

Effect of Depth and Width on Local Minima in Deep Learning

In this paper, we analyze the effects of depth and width on the quality ...

0 Kenji Kawaguchi, et al. ∙

Kenji Kawaguchi

Featured Co-authors