Search Results for author:
Found 19 papers, 6 papers with code
HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible.
AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception
Driver distraction has become a significant cause of severe traffic accidents over the past decade.
Contributions of Shape, Texture, and Color in Visual Recognition
We use human experiments to confirm that both HVE and humans predominantly use some specific features to support the classification of specific classes (e. g., texture is the dominant feature to distinguish a zebra from other quadrupeds, both for humans and HVE).
Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization
(2) They lack convexity constraints, which is important for meaningfully manipulating specific attributes for downstream tasks.
Towards Generic Interface for Human-Neural Network Knowledge Exchange
Take image classification as an example, HNI visualizes the reasoning logic of a NN with class-specific Structural Concept Graphs (c-SCG), which are human-interpretable.
A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts
Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability.
PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators
We consider offline reinforcement learning (RL) with heterogeneous agents under severe data scarcity, i. e., we only observe a single historical trajectory for every agent under an unknown, potentially sub-optimal policy.
Generative Auto-Encoder: Non-adversarial Controllable Synthesis with Disentangled Exploration
DEAE can become a generative model and synthesis semantic controllable samples by interpolating latent code, which can even synthesis novel attribute value never is shown in the original dataset.
Rethinking the Value of Labels for Improving Class-Imbalanced Learning
Real-world data often exhibits long-tailed distributions with heavy class imbalance, posing great challenges for deep recognition models.
Ranked #24 on
Long-tail Learning
on CIFAR-100-LT (ρ=50)
Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation
As our key contribution, we develop a simple, iterative learning algorithm that finds $\epsilon$-optimal $Q$-function with sample complexity of $\widetilde{O}(\frac{1}{\epsilon^{\max(d_1, d_2)+2}})$ when the optimal $Q$-function has low rank $r$ and the discounting factor $\gamma$ is below a certain threshold.
Stable Reinforcement Learning with Unbounded State Space
As a proof of concept, we propose an RL policy using Sparse-Sampling-based Monte Carlo Oracle and argue that it satisfies the stability property as long as the system dynamics under the optimal policy respects a Lyapunov function.
On Reinforcement Learning for Turn-based Zero-sum Markov Games
For a concrete instance of EIS where random policy is used for "exploration", Monte-Carlo Tree Search is used for "policy improvement" and Nearest Neighbors is used for "supervised learning", we establish that this method finds an $\varepsilon$-approximate value function of Nash equilibrium in $\widetilde{O}(\varepsilon^{-(d+4)})$ steps when the underlying state-space of the game is continuous and $d$-dimensional.
Harnessing Structures for Value-Based Planning and Reinforcement Learning
In this paper, we propose to exploit the underlying structures of the state-action value function, i. e., Q function, for both planning and deep RL.
ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation
We show that this process destroys the adversarial structure of the noise, while re-enforcing the global structure in the original image.
Understanding & Generalizing AlphaGo Zero
AlphaGo Zero (AGZ) introduced a new {\em tabula rasa} reinforcement learning algorithm that has achieved superhuman performance in the games of Go, Chess, and Shogi with no prior knowledge other than the rules of the game.
Non-Asymptotic Analysis of Monte Carlo Tree Search
In effect, we establish that to learn an $\varepsilon$ approximation of the value function with respect to $\ell_\infty$ norm, MCTS combined with nearest neighbor requires a sample size scaling as $\widetilde{O}\big(\varepsilon^{-(d+4)}\big)$, where $d$ is the dimension of the state space.
Machine Learning in Cyber-Security - Problems, Challenges and Data Sets
We present cyber-security problems of high importance.
Private Sequential Learning
We formulate a private learning model to study an intrinsic tradeoff between privacy and query complexity in sequential learning.
Robust GANs against Dishonest Adversaries
We explore a notion of robustness for generative adversarial models that is pertinent to their internal interactive structure, and show that, perhaps surprisingly, the GAN in its original form is not robust.
