Search Results for author:
Found 127 papers, 59 papers with code
CAiRE in DialDoc21: Data Augmentation for Information Seeking Dialogue System
Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on users’ needs, which.
CI-AVSR: A Cantonese Audio-Visual Speech Datasetfor In-car Command Recognition
With the rise of deep learning and intelligent vehicles, the smart assistant has become an essential in-car component to facilitate driving and provide extra functionalities.
Markov Chain-Guided Graph Construction and Sampling Depth Optimization for EEG-Based Mental Disorder Detection
Graph Neural Networks (GNNs) have received considerable attention since its introduction.
ImageBind-LLM: Multi-modality Instruction Tuning
During training, we adopt a learnable bind network to align the embedding space between LLaMA and ImageBind's image encoder.
Robotic Table Tennis: A Case Study into a High Speed Learning System
We present a deep-dive into a real-world robotic learning system that, in previous work, was shown to be capable of hundreds of table tennis rallies with a human and has the ability to precisely return the ball to desired targets.
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
To tackle this issue, we introduce an Omnidirectionally calibrated Quantization (OmniQuant) technique for LLMs, which achieves good performance in diverse quantization settings while maintaining the computational efficiency of PTQ by efficiently optimizing various quantization parameters.
FastSurfer-HypVINN: Automated sub-segmentation of the hypothalamus and adjacent structures on high-resolutional brain MRI
The hypothalamus plays a crucial role in the regulation of a broad range of physiological, behavioural, and cognitive functions.
RAVEN: In-Context Learning with Retrieval Augmented Encoder-Decoder Language Models
In this paper, we investigate the in-context learning ability of retrieval-augmented encoder-decoder language models.
When Super-Resolution Meets Camouflaged Object Detection: A Comparison Study
Super Resolution (SR) and Camouflaged Object Detection (COD) are two hot topics in computer vision with various joint applications.
Tiny LVLM-eHub: Early Multimodal Experiments with Bard
Secondly, it conducts an in-depth analysis of LVLMs' predictions using the ChatGPT Ensemble Evaluation (CEE), which leads to a robust and accurate evaluation and exhibits improved alignment with human evaluation compared to the word matching approach.
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Our goal is to enable a single end-to-end trained model to both learn to map robot observations to actions and enjoy the benefits of large-scale pretraining on language and vision-language data from the web.
Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
Large language models (LLMs) exhibit a wide range of promising capabilities -- from step-by-step planning to commonsense reasoning -- that may provide utility for robots, but remain prone to confidently hallucinated predictions.
Principles and Guidelines for Evaluating Social Robot Navigation Algorithms
A major challenge to deploying robots widely is navigation in human-populated environments, commonly referred to as social robot navigation.
Rethinking Cross-Entropy Loss for Stereo Matching Networks
Then a novel adaptive multi-modal cross-entropy loss which encourages the network to generate different distribution patterns for edge and non-edge pixels is proposed.
LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models
Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning.
Language to Rewards for Robotic Skill Synthesis
However, since low-level robot actions are hardware-dependent and underrepresented in LLM training corpora, existing efforts in applying LLMs to robotics have largely treated LLMs as semantic planners or relied on human-engineered control primitives to interface with the robot.
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers
Token compression aims to speed up large-scale vision transformers (e. g. ViTs) by pruning (dropping) or merging tokens.
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures.
MaskCL: Semantic Mask-Driven Contrastive Learning for Unsupervised Person Re-Identification with Clothes Change
This paper considers a novel and challenging problem: unsupervised long-term person re-identification with clothes change.
Ranked #1 on
Unsupervised Person Re-Identification
on PRCC
Clothes Changing Person Re-Identification
Contrastive Learning
+3
Feature Expansion for Graph Neural Networks
Graph neural networks aim to learn representations for graph-structured data and show impressive performance, particularly in node classification.
Advances in Deep Concealed Scene Understanding
Concealed scene understanding (CSU) is a hot computer vision topic aiming to perceive objects exhibiting camouflage.
Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
To answer it, we perform a comprehensive study on a scalable pre-trained retrieval-augmented LM (i. e., RETRO) compared with standard GPT and retrieval-augmented GPT incorporated at fine-tuning or inference stages.
SAM Struggles in Concealed Scenes -- Empirical Study on "Segment Anything"
Segmenting anything is a ground-breaking step toward artificial general intelligence, and the Segment Anything Model (SAM) greatly fosters the foundation models for computer vision.
High speed free-space optical communication using standard fiber communication component without optical amplification
Free-space optical communication (FSO) can achieve fast, secure and license-free communication without need for physical cables, making it a cost-effective, energy-efficient and flexible solution when the fiber connection is unavailable.
Short-length SSVEP data extension by a novel generative adversarial networks based framework
This study substantiates the feasibility of the proposed method to extend the data length for short-time SSVEP signals for developing a high-performance BCI system.
DeepChange: A Long-Term Person Re-Identification Benchmark with Clothes Change
Long-term re-id with clothes change is a challenging problem in surveillance AI.
RT-1: Robotics Transformer for Real-World Control at Scale
By transferring knowledge from large, diverse, task-agnostic datasets, modern machine learning models can solve specific downstream tasks either zero-shot or with small task-specific datasets to a high level of performance.
Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms
We describe the current content moderation strategy employed by Meta to remove policy-violating content from its platforms.
Evaluating Parameter Efficient Learning for Generation
For cross-domain and cross-dataset cases, we show that (a) Adapter (Houlsby et al., 2019) performs the best amongst all the PERMs studied here, and (b) it outperforms finetuning if the task dataset is below a certain size.
Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization
This problem is challenging, as it requires planning wiping actions while reasoning over uncertain latent dynamics of crumbs and spills captured via high-dimensional visual observations.
Context Generation Improves Open Domain Question Answering
Prior work on closed-book QA either directly finetunes or prompts a pretrained language model (LM) to leverage the stored knowledge.
A Transformer-based deep neural network model for SSVEP classification
The proposed model validates the feasibility of deep learning models based on Transformer structure for SSVEP classification task, and could serve as a potential model to alleviate the calibration procedure in the practical application of SSVEP-based BCI systems.
Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation
Despite decades of research, existing navigation systems still face real-world challenges when deployed in the wild, e. g., in cluttered home environments or in human-occupied public spaces.
Multimodal Learning with Transformers: A Survey
Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks.
Factuality Enhanced Language Models for Open-Ended Text Generation
In this work, we measure and improve the factual accuracy of large-scale LMs for open-ended text generation.
Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner
Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises.
TOD-CNN: An Effective Convolutional Neural Network for Tiny Object Detection in Sperm Videos
The detection of tiny objects in microscopic videos is a problematic point, especially in large-scale experiments.
Attention Mechanism based Cognition-level Scene Understanding
Given a question-image input, the Visual Commonsense Reasoning (VCR) model can predict an answer with the corresponding rationale, which requires inference ability from the real world.
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
We show how low-level skills can be combined with large language models so that the language model provides high-level knowledge about the procedures for performing complex and temporally-extended instructions, while value functions associated with these skills provide the grounding necessary to connect this knowledge to a particular physical environment.
QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation
Multi-hop question generation (MQG) aims to generate complex questions which require reasoning over multiple pieces of information of the input passage.
Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models
In this work, we systematically explore domain-adaptive training to reduce the toxicity of language models.
How to Understand Masked Autoencoders
"Masked Autoencoders (MAE) Are Scalable Vision Learners" revolutionizes the self-supervised learning method in that it not only achieves the state-of-the-art for image pre-training, but is also a milestone that bridges the gap between visual and linguistic masked autoencoding (BERT-style) pre-trainings.
Unsupervised Long-Term Person Re-Identification with Clothes Change
We investigate unsupervised person re-identification (Re-ID) with clothes change, a new challenging problem with more practical usability and scalability to real-world deployment.
Clustering
Unsupervised Long Term Person Re-Identification
+1
CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition
With the rise of deep learning and intelligent vehicle, the smart assistant has become an essential in-car component to facilitate driving and provide extra functionalities.
Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset
We further conduct experiments with Fairseq S2T Transformer, a state-of-the-art ASR model, on the biggest existing dataset, Common Voice zh-HK, and our proposed MDCC, and the results show the effectiveness of our dataset.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation
ASCEND (A Spontaneous Chinese-English Dataset) is a high-quality Mandarin Chinese-English code-switching corpus built on spontaneous multi-turn conversational dialogue sources collected in Hong Kong.
Hierarchical Neural Data Synthesis for Semantic Parsing
Moreover, even the questions pertinent to a given domain, which are the input of a semantic parsing system, might not be readily available, especially in cross-domain semantic parsing.
Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
Hierarchical reinforcement learning aims to enable this by providing a bank of low-level skills as action abstractions.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Contrastive Document Representation Learning with Graph Attention Networks
In this work, we propose to use a graph attention network on top of the available pretrained Transformers model to learn document embeddings.
Attention-guided Generative Models for Extractive Question Answering
We propose a simple strategy to obtain an extractive answer span from the generative model by leveraging the decoder cross-attention patterns.
Extractive Question-Answering
Open-Domain Question Answering
+1
Multiplicative Position-aware Transformer Models for Language Understanding
Transformer models, which leverage architectural improvements like self-attention, perform remarkably well on Natural Language Processing (NLP) tasks.
Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering
However, a large amount of world's knowledge is stored in structured databases, and need to be accessed using query languages such as SQL.
Turing: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface
A natural language database interface (NLDB) can democratize data-driven insights for non-technical users.
CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System
Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on users' needs, which.
X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing
Experimental results illustrate that our model can significantly outperform existing strong baselines in cross-lingual and cross-domain settings, and our model can also achieve a good generalization ability on target languages of target domains.
BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling
However, existing datasets for end-to-end ToD modeling are limited to a single language, hindering the development of robust end-to-end ToD systems for multilingual countries and regions.
DeepChange: A Large Long-Term Person Re-Identification Benchmark with Clothes Change
Currently, one of the most significant limitations in this field is the lack of a large realistic benchmark.
Revealing and controlling nuclear dynamics following inner-shell photoionization of N2
In this work, we apply the Monte Carlo wave packet method to study the ultrafast nuclear dynamics following inner-shell photoionization of N2 exposed to an ultrashort intense X-ray pulse.
Atomic Physics Atomic and Molecular Clusters
Optimizing Deeper Transformers on Small Datasets
This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension.
Mobile Robots Exploration via Deep Reinforcement Learning
n this paper, we try to solve the mobile robot exploration problem in a 2D indoor office environment by deep reinforcement learning.
Unsupervised Regionalization of Particle-resolved Aerosol Mixing State Indices on the Global Scale
Here we developed a simple but effective unsupervised learning approach to regionalize predictions of global aerosol mixing state indices.
The Twelvefold Way of Non-Sequential Lossless Compression
Many information sources are not just sequences of distinguishable symbols but rather have invariances governed by alternative counting paradigms such as permutations, combinations, and partitions.
Information Theory Information Theory
MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models
We showcase the controllability of our model by replacing the keywords used to generate stories and re-running the generation process.
Cross-lingual Spoken Language Understanding with Regularized Representation Alignment
Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the performance sub-optimal.
Improve Transformer Models with Better Relative Position Embeddings
In this paper, we first review absolute position embeddings and existing methods for relative position embeddings.
Embedding-based Zero-shot Retrieval through Query Generation
In some cases, our model trained on synthetic data can even outperform the same model trained on real data
EmoGraph: Capturing Emotion Correlations using Graph Networks
Most emotion recognition methods tackle the emotion understanding task by considering individual emotion independently while ignoring their fuzziness nature and the interconnections among them.
Ranked #3 on
Emotion Classification
on SemEval 2018 Task 1E-c
Extension of causal decomposition in the mutual complex dynamic process
Causal decomposition depicts a cause-effect relationship that is not based on the concept of prediction, but based on the phase dependence of time series.
On Learning Semantic Representations for Million-Scale Free-Hand Sketches
Specifically, we use our dual-branch architecture as a universal representation framework to design two sketch-specific deep models: (i) We propose a deep hashing model for sketch retrieval, where a novel hashing loss is specifically designed to accommodate both the abstract and messy traits of sketches.
Meta-Transfer Learning for Code-Switched Speech Recognition
An increasing number of people in the world today speak a mixed-language as a result of being multilingual.
Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling
In this paper, we propose a Coarse-to-fine approach (Coach) for cross-domain slot filling.
Cross-Domain Named Entity Recognition
named-entity-recognition
+3
Variational Transformers for Diverse Response Generation
Despite the great promise of Transformers in many sequence modeling tasks (e. g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation.
TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding
Prior to the transformer era, bidirectional Long Short-Term Memory (BLSTM) has been the dominant modeling architecture for neural machine translation and question answering.
Ranked #1 on
Text Classification
on GLUE RTE
Learning Fast Adaptation on Cross-Accented Speech Recognition
The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic speech recognition (ASR) system.
Audio and Speech Processing Sound
Fine-Grained Instance-Level Sketch-Based Video Retrieval
Existing sketch-analysis work studies sketches depicting static objects or scenes.
Learning to Walk in the Real World with Minimal Human Effort
In this paper, we develop a system for learning legged locomotion policies with deep RL in the real world with minimal human effort.
Deep Self-Supervised Representation Learning for Free-Hand Sketch
In this paper, we tackle for the first time, the problem of self-supervised representation learning for free-hand sketches.
EEG-based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and their Applications
Recent technological advances such as wearable sensing devices, real-time data streaming, machine learning, and deep learning approaches have increased interest in electroencephalographic (EEG) based BCI for translational and healthcare applications.
Deep Learning for Free-Hand Sketch: A Survey
Free-hand sketches are highly illustrative, and have been widely used by humans to depict objects or stories from ancient times to the present.
Multi-Graph Transformer for Free-Hand Sketch Recognition
In this work, we propose a new representation of sketches as multiple sparsely connected graphs.
SPIN: A High Speed, High Resolution Vision Dataset for Tracking and Action Recognition in Ping Pong
The corpus consists of ping pong play with three main annotation streams that can be used to learn tracking and action recognition models -- tracking of the ping pong ball and poses of humans in the videos and the spin of the ball being hit by humans.
Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems
Recently, data-driven task-oriented dialogue systems have achieved promising performance in English.
Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables
Despite the surging demands for multilingual task-oriented dialog systems (e. g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios.
Fault Detection and Identification using Bayesian Recurrent Neural Networks
In processing and manufacturing industries, there has been a large push to produce higher quality products and ensure maximum efficiency of processes.
Generalizing Question Answering System with Pre-trained Language Model Fine-tuning
With a large number of datasets being released and new techniques being proposed, Question answering (QA) systems have witnessed great breakthroughs in reading comprehension (RC)tasks.
Domain Adaptation with BERT-based Domain Classification and Data Selection
The performance of deep neural models can deteriorate substantially when there is a domain shift between training and test data.
Boosting Image Recognition with Non-differentiable Constraints
In this paper, we study the problem of image recognition with non-differentiable constraints.
Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning
Sensational headlines are headlines that capture people's attention and generate reader interest.
MoEL: Mixture of Empathetic Listeners
Previous research on empathetic dialogue systems has mostly focused on generating responses given certain emotions.
Getting To Know You: User Attribute Extraction from Dialogues
User attributes provide rich and useful information for user understanding, yet structured and easy-to-use attributes are often sparsely populated.
Multi-view Clustering with the Cooperation of Visible and Hidden Views
The existing algorithms usually focus on the cooperation of different views in the original space but neglect the influence of the hidden information among these different visible views, or they only consider the hidden information between the views.
Multi-View Fuzzy Clustering with The Alternative Learning between Shared Hidden Space and Partition
How to exploit the relation-ship between different views effectively using the characteristic of multi-view data has become a crucial challenge.
CAiRE: An Empathetic Neural Chatbot
In this paper, we present an end-to-end empathetic conversation agent CAiRE.
Generating Empathetic Responses by Looking Ahead the User's Sentiment
Hence, in this paper, we propose Sentiment Look-ahead, which is a novel perspective for empathy that models the future user emotional state.
CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification
Detecting emotion from dialogue is a challenge that has not yet been extensively surveyed.
CAiRE\_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification
Detecting emotion from dialogue is a challenge that has not yet been extensively surveyed.
Better Long-Range Dependency By Bootstrapping A Mutual Information Regularizer
In this work, we develop a novel regularizer to improve the learning of long-range dependency of sequence data.
A Cross-Domain Transferable Neural Coherence Model
Coherence is an important aspect of text quality and is crucial for ensuring its readability.
On Variational Learning of Controllable Representations for Text without Supervision
The variational autoencoder (VAE) can learn the manifold of natural images on certain datasets, as evidenced by meaningful interpolating or extrapolating in the continuous latent space.
Deep Image Feature Learning with Fuzzy Rules
The method progressively learns image features through a layer-by-layer manner based on fuzzy rules, so the feature learning process can be better explained by the generated rules.
Multi-view Information-theoretic Co-clustering for Co-occurrence Data
More specifically, it exploits the agreement and disagreement among views by sharing a common clustering results along the sample dimension and keeping the clustering results of each view specific along the feature dimension.
Joint Information Preservation for Heterogeneous Domain Adaptation
The two domains often lie in different feature spaces due to diverse data collection methods, which leads to the more challenging task of heterogeneous domain adaptation (HDA).
Passage Ranking with Weak Supervision
In this paper, we propose a \textit{weak supervision} framework for neural ranking tasks based on the data programming paradigm \citep{Ratner2016}, which enables us to leverage multiple weak supervision signals from different sources.
Deep Zero-Shot Learning for Scene Sketch
We introduce a novel problem of scene sketch zero-shot learning (SSZSL), which is a challenging task, since (i) different from photo, the gap between common semantic domain (e. g., word vector) and sketch is too huge to exploit common semantic knowledge as the bridge for knowledge transfer, and (ii) compared with single-object sketch, more expressive feature representation for scene sketch is required to accommodate its high-level of abstraction and complexity.
Concise Fuzzy System Modeling Integrating Soft Subspace Clustering and Sparse Learning
Furthermore, for highly nonlinear modeling task, it is usually necessary to use a large number of rules which further weakens the clarity and interpretability of TSK FS.
Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction
Knowledge Bases (KBs) require constant up-dating to reflect changes to the world they represent.
Ranked #3 on
Relation Extraction
on NYT Corpus
A novel repetition normalized adversarial reward for headline generation
While reinforcement learning can effectively improve language generation models, it often suffers from generating incoherent and repetitive phrases \cite{paulus2017deep}.
Transfer Representation Learning with TSK Fuzzy System
A core issue in transfer learning is to learn a shared feature space in where the distributions of the data from two domains are matched.
Trust Region Based Adversarial Attack on Neural Networks
To address this problem, we present a new family of trust region based adversarial attacks, with the goal of computing adversarial perturbations efficiently.
Newton-MR: Inexact Newton Method With Minimum Residual Sub-problem Solver
We consider a variant of inexact Newton Method, called Newton-MR, in which the least-squares sub-problems are solved approximately using Minimum Residual method.
Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
In this paper, we propose Emo2Vec which encodes emotional semantics into vectors.
Ranked #28 on
Sentiment Analysis
on SST-5 Fine-grained classification
Anomaly Detection for Skin Disease Images Using Variational Autoencoder
If we focus on specific diseases, the model is able to detect melanoma with 0. 864 AUCROC and detect actinic keratosis with 0. 872 AUCROC, even if it only sees the images of nevus.
PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and \#hashtags
This paper describes our system that has been submitted to SemEval-2018 Task 1: Affect in Tweets (AIT) to solve five subtasks.
PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and #hashtags
This paper describes our system that has been submitted to SemEval-2018 Task 1: Affect in Tweets (AIT) to solve five subtasks.
SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval
Key to our network design is the embedding of unique characteristics of human sketch, where (i) a two-branch CNN-RNN architecture is adapted to explore the temporal ordering of strokes, and (ii) a novel hashing loss is specifically designed to accommodate both the temporal and abstract traits of sketches.
Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss
The task of Fine-grained Entity Type Classification (FETC) consists of assigning types from a hierarchy to entity mentions in text.
Investigations on Knowledge Base Embedding for Relation Prediction and Extraction
We report an evaluation of the effectiveness of the existing knowledge base embedding models for relation prediction and for relation extraction on a wide range of benchmarks.
GIANT: Globally Improved Approximate Newton Method for Distributed Optimization
For distributed computing environment, we consider the empirical risk minimization problem and propose a distributed and communication-efficient Newton-type optimization method.
Second-Order Optimization for Non-Convex Machine Learning: An Empirical Study
While first-order optimization methods such as stochastic gradient descent (SGD) are popular in machine learning (ML), they come with well-known deficiencies, including relatively-slow convergence, sensitivity to the settings of hyper-parameters such as learning rate, stagnation at high training errors, and difficulty in escaping flat regions and saddle points.
Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information
In this light, we consider the canonical problem of finite-sum minimization, provide appropriate uniform and non-uniform sub-sampling strategies to construct such Hessian approximations, and obtain optimal iteration complexity for the corresponding sub-sampled trust-region and cubic regularization methods.
Accelerated Stochastic Power Iteration
We propose a simple variant of the power iteration with an added momentum term, that achieves both the optimal sample and iteration complexity.
Cross-modal Subspace Learning for Fine-grained Sketch-based Image Retrieval
Sketch-based image retrieval (SBIR) is challenging due to the inherent domain-gap between sketch and photo.
Ranked #5 on
Sketch-Based Image Retrieval
on Chairs
Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data
Prior work has explored learning accuracies for these sources even without ground truth labels, but they assume that a single accuracy parameter is sufficient to model the behavior of these sources over the entire training set.
Sub-sampled Newton Methods with Non-uniform Sampling
As second-order methods prove to be effective in finding the minimizer to a high-precision, in this work, we propose randomized Newton-type algorithms that exploit \textit{non-uniform} sub-sampling of $\{\nabla^2 f_i(w)\}_{i=1}^{n}$, as well as inexact updates, as means to reduce the computational complexity.
Learning Subclass Representations for Visually-varied Image Classification
The novelty of the approach is that subclass representations make use of not only the content of the photos themselves, but also information on the co-occurrence of their tags, which determines membership in both subclasses and top-level classes.
Short-Term Depression in VLSI Stochastic Synapse
We report a compact realization of short-term depression (STD) in a VLSI stochastic synapse.
