Search Results for author:
Found 84 papers, 26 papers with code
On Implicit Regularization in $\beta$-VAEs
While the impact of variational inference (VI) on posterior inference in a fixed generative model is well-characterized, its role in regularizing a learned generative model when used in variational autoencoders (VAEs) is poorly understood.
The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations
Modern machine learning models are prone to over-reliance on spurious correlations, which can often lead to poor performance on minority groups.
Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Large language models (LLMs), even when specifically trained to process long input contexts, struggle to capture relevant information located in the middle of their input.
Efficient Human Pose Estimation: Leveraging Advanced Techniques with MediaPipe
This study presents significant enhancements in human pose estimation using the MediaPipe framework.
RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control
Existing training-free approaches exhibit difficulties in (a) style extraction from reference images in the absence of additional style or content text descriptions, (b) unwanted content leakage from reference style images, and (c) effective composition of style and content.
Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
Using various datasets and prompting techniques that encourage model introspection, we probe the alignment between models' internal and expressed confidence.
Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models
Research on Large Language Models (LLMs) has often neglected subtle biases that, although less apparent, can significantly influence the models' outputs toward particular social narratives.
Score-based Causal Representation Learning: Linear and General Transformations
The paper addresses both the identifiability and achievability aspects.
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
To do so, we investigate a simple self-training method based on expectation-maximization, which we call ReST$^{EM}$, where we (1) generate samples from the model and filter them using binary feedback, (2) fine-tune the model on these samples, and (3) repeat this process a few times.
Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion
To our best knowledge, this is the first work to offer an efficient second-order approximation in solving inverse problems using latent diffusion and editing real-world images with corruptions.
Enhancing Clustering Representations with Positive Proximity and Cluster Dispersion Learning
PIPCDR incorporates a positive instance proximity loss and a cluster dispersion regularizer.
Player Re-Identification Using Body Part Appearences
Our model consists of a two-stream network (one stream for appearance map extraction and the other for body part map extraction) and a bilinear-pooling layer that generates and spatially pools the body part map.
Robust Unsupervised Domain Adaptation by Retaining Confident Entropy via Edge Concatenation
To address this issue, we introduce a novel approach to domain adaptation, leveraging the synergy of internal and external information within entropy-based adversarial networks.
Small-scale proxies for large-scale Transformer training instabilities
In this work, we seek ways to reproduce and study training stability and instability at smaller scales.
Distributionally Robust Post-hoc Classifiers under Prior Shifts
We investigate the problem of training models that are robust to shifts caused by changes in the distribution of class-priors or group-priors.
Towards Last-layer Retraining for Group Robustness with Fewer Annotations
In this work, we examine this impractical requirement and find that last-layer retraining can be surprisingly effective with no group annotations (other than for model selection) and only a handful of class annotations.
Learnable Digital Twin for Efficient Wireless Network Evaluation
Network digital twins (NDTs) facilitate the estimation of key performance indicators (KPIs) before physically implementing a network, thereby enabling efficient optimization of the network configuration.
Early Weight Averaging meets High Learning Rates for LLM Pre-training
Specifically, we pre-trained nanoGPT-2 models of varying sizes, small (125M), medium (335M), and large (770M)on the OpenWebText dataset, comprised of 9B tokens.
RemoteNet: Remote Sensing Image Segmentation Network based on Global-Local Information
It becomes challenging to capture the underlying attributes in the global and local context for their segmentation.
Rewarded meta-pruning: Meta Learning with Rewards for Channel Pruning
Convolutional Neural Networks (CNNs) have a large number of parameters and take significantly large hardware resources to compute, so edge devices struggle to run high-level networks.
Score-based Causal Representation Learning with Interventions
The objectives are: (i) recovering the unknown linear transformation (up to scaling) and (ii) determining the directed acyclic graph (DAG) underlying the latent variables.
Trial-Based Dominance Enables Non-Parametric Tests to Compare both the Speed and Accuracy of Stochastic Optimizers
Non-parametric tests can determine the better of two stochastic optimization algorithms when benchmarking results are ordinal, like the final fitness values of multiple trials.
To Aggregate or Not? Learning with Separate Noisy Labels
The rawly collected training data often comes with separate noisy labels collected from multiple imperfect annotators (e. g., via crowdsourcing).
GridShift: A Faster Mode-seeking Algorithm for Image Segmentation and Object Tracking
To address this issue, we propose a mode-seeking algorithm called GridShift, with significant speedup and principally based on MS. To accelerate, GridShift employs a grid-based approach for neighbor search, which is linear in the number of data points.
Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration
We claim that to support the constantly growing requirements of intelligent applications in the device-edge-cloud computing continuum, resource orchestration needs to embrace edge AI and emphasize local autonomy and intelligence.
DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents
Diffusion probabilistic models have been shown to generate state-of-the-art results on several competitive image synthesis benchmarks but lack a low-dimensional, interpretable latent space, and are slow at generation.
Ranked #18 on
Image Generation
on CelebA 64x64
Solving Inverse Problems with NerfGANs
We introduce a novel framework for solving inverse problems using NeRF-style generative models.
When Creators Meet the Metaverse: A Survey on Computational Arts
The metaverse, enormous virtual-physical cyberspace, has brought unprecedented opportunities for artists to blend every corner of our physical surroundings with digital creativity.
Constrained Instance and Class Reweighting for Robust Learning under Label Noise
However, their performance is largely dependent on the quality of the training data and often degrades in the presence of noise.
Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications
Our findings suggest that replay with exemplars-based schemes such as iCaRL has the best performance trade-offs, even in complex scenarios, at the expense of some storage space (few MBs) for training examples (1% to 5%).
Distance Based Pattern Driven Mining for Outlier Detection in High Dimensional Big Dataset
Detection of outliers or anomalies is one of the vital issues in pattern-driven data mining.
Implicit Rate-Constrained Optimization of Non-decomposable Objectives
We consider a popular family of constrained optimization problems arising in machine learning that involve optimizing a non-decomposable evaluation metric with a certain thresholded form, while constraining another metric of interest.
Wavelet Design in a Learning Framework
Wavelets have proven to be highly successful in several signal and image processing applications.
Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval
We present Retrieve in Style (RIS), an unsupervised framework for facial feature transfer and retrieval on real images.
Physics-Guided Deep Neural Network to Characterize Non-Newtonian Fluid Flow for Optimal Use of Energy Resources
The uncertainty in fluid consistency index is responsible for higher variance in the calculated flow rate, while the least variation is observed due to fluid behavior index uncertainty.
Risk score learning for COVID-19 contact tracing apps
Although this data is already being collected (in an aggregated, privacy-preserving way) by several health authorities, in this paper we limit ourselves to simulated data, so that we can systematically study the different factors that affect the feasibility of the approach.
A Unified Bayesian Framework for Discriminative and Generative Continual Learning
Two notable directions among the recent advances in continual learning with neural networks are (1) variational Bayes based regularization by learning priors from previous tasks, and, (2) learning the structure of deep networks to adapt to new tasks.
Floquet Gauge Pumps as Sensors for Spectral Degeneracies Protected by Symmetry or Topology
The dynamically generated magnetization current depends on the phases of complex coupling terms, with the XY interaction as the real and DMI as the imaginary part.
Quantum Gases Mesoscale and Nanoscale Physics Superconductivity
A thermodynamic probe of the topological phase transition in epitaxial graphene based Floquet topological insulator
In this paper, we probe the topological phase transition of an FTI via the efficiency and work output of quantum Otto and quantum Stirling heat engines.
Mesoscale and Nanoscale Physics Applied Physics Quantum Physics
Score-Based Generative Modeling through Stochastic Differential Equations
Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9. 89 and FID of 2. 20, a competitive likelihood of 2. 99 bits/dim, and demonstrate high fidelity generation of 1024 x 1024 images for the first time from a score-based generative model.
Ranked #5 on
Density Estimation
on CIFAR-10
Adaptive Contention Window Design using Deep Q-learning
We study the problem of adaptive contention window (CW) design for random-access wireless networks.
Few-Shot Adaptation of Generative Adversarial Networks
We validate our method in a challenging few-shot setting of 5-100 images in the target domain.
Generalized Adversarially Learned Inference
Recent approaches, such as ALI and BiGAN frameworks, develop methods of inference of latent variables in GANs by adversarially training an image generator along with an encoder to match two joint distributions of image and latent vector pairs.
MCQA: Multimodal Co-attention Based Network for Question Answering
We present MCQA, a learning-based algorithm for multimodal question answering.
On the Inhibition of COVID-19 Protease by Indian Herbal Plants: An In Silico Investigation
This study aims to assess the Indian herbal plants in the pursuit of potential COVID-19 inhibitors using in silico approaches.
Marketplace for AI Models
Artificial intelligence shows promise for solving many practical societal problems in areas such as healthcare and transportation.
Regularized Autoencoders via Relaxed Injective Probability Flow
Invertible flow-based generative models are an effective method for learning to generate samples, while allowing for tractable likelihood computation and inference.
On Implicit Regularization in $β$-VAEs
While the impact of variational inference (VI) on posterior inference in a fixed generative model is well-characterized, its role in regularizing a learned generative model when used in variational autoencoders (VAEs) is poorly understood.
Bayesian Structure Adaptation for Continual Learning
Two notable directions among the recent advances in continual learning with neural networks are ($i$) variational Bayes based regularization by learning priors from previous tasks, and, ($ii$) learning the structure of deep networks to adapt to new tasks.
Emotion helps Sentiment: A Multi-task Model for Sentiment and Emotion Analysis
Our network also boosts the performance of emotion analysis by 5 F-score points on Stance Sentiment Emotion Corpus.
Customized video filtering on YouTube
But with a huge surge in content being posted online it becomes seemingly difficult to filter out related videos on which they can run their ads without compromising brand name.
Weakly Supervised Disentanglement with Guarantees
Learning disentangled representations that correspond to factors of variation in real-world data is critical to interpretable and human-controllable machine learning.
Refined $α$-Divergence Variational Inference via Rejection Sampling
Our inference method is based on a crucial observation that $D_\infty(p||q)$ equals $\log M(\theta)$ where $M(\theta)$ is the optimal value of the RS constant for a given proposal $q_\theta(x)$.
Multilingual and Multitarget Hate Speech Detection in Tweets
Social media networks have become a space where users are free to relate their opinions and sentiments which may lead to a large spreading of hatred or abusive messages which have to be moderated.
The binary trio at SemEval-2019 Task 5: Multitarget Hate Speech Detection in Tweets
The massive growth of user-generated web content through blogs, online forums and most notably, social media networks, led to a large spreading of hatred or abusive messages which have to be moderated.
Language-Agnostic Model for Aspect-Based Sentiment Analysis
In this paper, we propose a language-agnostic deep neural network architecture for aspect-based sentiment analysis.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
A Scale Invariant Flatness Measure for Deep Network Minima
It has been empirically observed that the flatness of minima obtained from training deep networks seems to correlate with better generalization.
Understanding Unequal Gender Classification Accuracy from Face Images
Recent work shows unequal performance of commercial face classification services in the gender classification task across intersectional groups defined by skin type and gender.
SpotTune: Transfer Learning through Adaptive Fine-tuning
Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision.
MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Prediction
Some of the major challenges involved in developing such models are, (i) limited availability of materials data as compared to other fields, (ii) lack of universal descriptor of materials to predict its various properties.
Ranked #4 on
Band Gap
on Materials Project
Co-regularized Alignment for Unsupervised Domain Adaptation
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source domain}.
Delta-encoder: an effective sample synthesis method for few-shot object recognition
Our approach is based on a modified auto-encoder, denoted Delta-encoder, that learns to synthesize new samples for an unseen category just by seeing few examples from it.
Knowledge-enriched Two-layered Attention Network for Sentiment Analysis
We propose a novel two-layered attention network based on Bidirectional Long Short-Term Memory for sentiment analysis.
Avoiding Catastrophic States with Intrinsic Fear
Many practical reinforcement learning problems contain catastrophic states that the optimal policy visits infrequently or never.
BlockDrop: Dynamic Inference Paths in Residual Networks
Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications.
The Riemannian Geometry of Deep Generative Models
Deep generative models learn a mapping from a low dimensional latent space to a high-dimensional data space.
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
Disentangled representations, where the higher level data generative factors are reflected in disjoint latent dimensions, offer several benefits such as ease of deriving invariant representations, transferability to other tasks, interpretability, etc.
A Multilayer Perceptron based Ensemble Technique for Fine-grained Financial Sentiment Analysis
In this paper, we propose a novel method for combining deep learning and classical feature based models using a Multi-Layer Perceptron (MLP) network for financial sentiment analysis.
SenGen: Sentence Generating Neural Variational Topic Model
We present a new topic model that generates documents by sampling a topic for one whole sentence at a time, and generating the words in the sentence using an RNN decoder that is conditioned on the topic of the sentence.
IITPB at SemEval-2017 Task 5: Sentiment Prediction in Financial Text
The other system was based on Support Vector Regression using word embeddings, lexicon features, and PMI scores as features.
Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
Semi-supervised learning methods using Generative Adversarial Networks (GANs) have shown promising empirical success recently.
Local Group Invariant Representations via Orbit Embeddings
We consider transformations that form a \emph{group} and propose an approach based on kernel methods to derive local group invariant representations.
S3Pool: Pooling with Stochastic Spatial Sampling
We view the pooling operation in CNNs as a two-step procedure: first, a pooling window (e. g., $2\times 2$) slides over the feature map with stride one which leaves the spatial resolution intact, and second, downsampling is performed by selecting one pixel from each non-overlapping pooling window in an often uniform and deterministic (e. g., top-left) manner.
Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification
Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them.
Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear
We introduce intrinsic fear (IF), a learned reward shaping that guards DRL agents against periodic catastrophes.
A new Initial Centroid finding Method based on Dissimilarity Tree for K-means Algorithm
Cluster analysis is one of the primary data analysis technique in data mining and K-means is one of the commonly used partitioning clustering algorithm.
Exact and Heuristic Algorithms for Semi-Nonnegative Matrix Factorization
Second, we propose an exact algorithm (that is, an algorithm that finds an optimal solution), also based on the SVD, for a certain class of matrices (including nonnegative irreducible matrices) from which we derive an initialization for matrices not belonging to that class.
Near-separable Non-negative Matrix Factorization with $\ell_1$- and Bregman Loss Functions
Recently, a family of tractable NMF algorithms have been proposed under the assumption that the data matrix satisfies a separability condition Donoho & Stodden (2003); Arora et al. (2012).
Simultaneously Leveraging Output and Task Structures for Multiple-Output Regression
In this paper, we present a multiple-output regression model that leverages the covariance structure of the functions (i. e., how the multiple functions are related with each other) as well as the conditional covariance structure of the outputs.
Learning Task Grouping and Overlap in Multi-task Learning
In the paradigm of multi-task learning, mul- tiple related prediction tasks are learned jointly, sharing information across the tasks.
Co-regularized Multi-view Spectral Clustering
In many clustering problems, we have access to multiple views of the data each of which could be individually used for clustering.
Co-regularization Based Semi-supervised Domain Adaptation
This paper presents a co-regularization based approach to semi-supervised domain adaptation.
