Search Results for author:
Found 17 papers, 7 papers with code
AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale
Active Visual Exploration (AVE) is a task that involves dynamically selecting observations (glimpses), which is critical to facilitate comprehension and navigation within an environment.
Scaling Laws for Fine-Grained Mixture of Experts
Our findings not only show that MoE models consistently outperform dense Transformers but also highlight that the efficiency gap between dense and MoE models widens as we scale up the model size and training budget.
SADMoE: Exploiting Activation Sparsity with Dynamic-k Gating
Transformer models, despite their impressive performance, often face practical limitations due to their high computational requirements.
Pre-Pruning and Gradient-Dropping Improve Differentially Private Image Classification
To tackle this challenge, we take advantage of the fact that neural networks are overparameterized, which allows us to improve neural network training with differential privacy.
Lidar Line Selection with Spatially-Aware Shapley Value for Cost-Efficient Depth Completion
Lidar is a vital sensor for estimating the depth of a scene.
Differential Privacy Meets Neural Network Pruning
We study the interplay between neural network pruning and differential privacy, through the two modes of parameter updates.
Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation
Maximum mean discrepancy (MMD) is a particularly useful distance metric for differentially private data generation: when used with finite-dimensional features it allows us to summarize and privatize the data distribution once, which we can repeatedly use during generator training without further privacy loss.
Revisiting Random Channel Pruning for Neural Network Compression
The proposed approach provides a new way to compare different methods, namely how well they behave compared with random pruning.
Hermite Polynomial Features for Private Data Generation
Hence, a relatively low order of Hermite polynomial features can more accurately approximate the mean embedding of the data distribution compared to a significantly higher number of random features.
Dirichlet Pruning for Neural Network Compression
We introduce Dirichlet pruning, a novel post-processing technique to transform a large neural network model into a compressed one.
Bayesian Importance of Features (BIF)
We introduce a simple and intuitive framework that provides quantitative explanations of statistical models through the probabilistic assessment of input feature importance.
DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation
We propose a differentially private data generation paradigm using random feature representations of kernel mean embeddings when comparing the distribution of true data with that of synthetic data.
Neuron ranking -- an informed way to condense convolutional neural networks architecture
Convolutional neural networks (CNNs) in recent years have made a dramatic impact in science, technology and industry, yet the theoretical mechanism of CNN architecture design remains surprisingly vague.
Radial and Directional Posteriors for Bayesian Neural Networks
We propose a new variational family for Bayesian neural networks.
Subgraph Matching Using Compactness Prior for Robust Feature Correspondence
By constructing Markov chain on the restricted search space instead of the original solution space, our method approximates the solution effectively.
How good is the Shapley value-based approach to the influence maximization problem?
Intuitively, since the Shapley value evaluates the average marginal contribution of a player to the coalitional game, it can be used in the network context to evaluate the marginal contribution of a node in the process of information diffusion given various groups of already 'infected' nodes.
