Search Results for author:
Found 38 papers, 13 papers with code
On the Importance of Gradient Norm in PAC-Bayesian Bounds
Generalization bounds which assess the difference between the true risk and the empirical risk, have been studied extensively.
A Functional Information Perspective on Model Interpretation
This work suggests a theoretical framework for model interpretability by measuring the contribution of relevant features to the functional entropy of the network with respect to the input.
Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images
Recently, attention mechanisms have shown compelling results both in their predictive performance and in their interpretable qualities.
Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies
Discrete variational auto-encoders (VAEs) are able to represent semantic latent spaces in generative learning.
Latent Space Explanation by Intervention
The success of deep neural nets heavily relies on their ability to encode complex relations between their input and their output.
Learning Generalized Gumbel-max Causal Mechanisms
To perform counterfactual reasoning in Structural Causal Models (SCMs), one needs to know the causal mechanisms, which provide factorizations of conditional distributions into noise sources and deterministic functions mapping realizations of noise to samples.
Video and Text Matching with Conditioned Embeddings
Traditionally video and text matching is done by learning a shared embedding space and the encoding of one modality is independent of the other.
Mixing between the Cross Entropy and the Expectation Loss Terms
The cross entropy loss is widely used due to its effectiveness and solid theoretical grounding.
Visual Navigation with Spatial Attention
This combination of the "what" and the "where" allows the agent to navigate toward the sought-after object effectively.
Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy
This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy.
Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies
However, regularization with the functional entropy is challenging.
Ranked #3 on
Visual Question Answering (VQA)
on VQA-CP
Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
For deep neural network accelerators, memory movement is both energetically expensive and can bound computation.
Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization
In this work, we learn the variance of these randomized structured predictors and show that it balances better between the learned score function and the randomized noise in structured prediction.
Generalized Planning With Deep Reinforcement Learning
A hallmark of intelligence is the ability to deduce general principles from examples, which are correct beyond the range of those observed.
On the generalization of bayesian deep nets for multi-class classification
Generalization bounds which assess the difference between the true risk and the empirical risk have been studied extensively.
A Formal Approach to Explainability
We regard explanations as a blending of the input sample and the model's output and offer a few definitions that capture various desired properties of the function that generates these explanations.
Direct Optimization through \arg \max for Discrete Variational Auto-Encoder
Reparameterization of variational auto-encoders with continuous random variables is an effective method for reducing the variance of their gradient estimates.
PAC-Bayesian Neural Network Bounds
Bayesian neural networks, which both use the negative log-likelihood loss function and average their predictions using a learned posterior over the parameters, have been used successfully across many scientific fields, partly due to their ability to `effortlessly' extract desired representations from many large-scale datasets.
Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces
A main benefit of DirPG algorithms is that they allow the insertion of domain knowledge in the form of upper bounds on return-to-go at training time, like is used in heuristic search, while still directly computing a policy gradient.
Factor Graph Attention
We address this issue and develop a general attention mechanism for visual dialog which operates on any number of data utilities.
Ranked #1 on
Visual Dialog
on VisDial v0.9 val
Perturbation Based Learning for Structured NLP Tasks with Application to Dependency Parsing
In this paper we propose a perturbation-based approach where sampling from a probabilistic model is computationally efficient.
Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder
We demonstrate empirically the effectiveness of the direct loss minimization technique in variational autoencoders with both unstructured and structured discrete latent variables.
High-Order Attention Models for Visual Question Answering
The quest for algorithms that enable cognitive abilities is an important part of machine learning.
Tight Bounds for Bandit Combinatorial Optimization
We revisit the study of optimal regret rates in bandit combinatorial optimization---a fundamental framework for sequential decision making under uncertainty that abstracts numerous combinatorial prediction problems.
Co-segmentation for Space-Time Co-located Collections
Thus, to disambiguate what the common foreground object is, we introduce a weakly-supervised technique, where we assume only a small seed, given in the form of a single segmented image.
Constraints Based Convex Belief Propagation
Inference in Markov random fields subject to consistency structure is a fundamental problem that arises in many real-life applications.
Online Learning with Feedback Graphs Without the Graphs
We study an online learning framework introduced by Mannor and Shamir (2011) in which the feedback is specified by a graph, in a setting where the graph may vary from round to round and is \emph{never fully revealed} to the learner.
High Dimensional Inference with Random Maximum A-Posteriori Perturbations
This paper shows that the expected value of perturb-max inference with low dimensional perturbations can be used sequentially to generate unbiased samples from the Gibbs distribution.
Multicuts and Perturb & MAP for Probabilistic Graph Clustering
We present a probabilistic graphical model formulation for the graph clustering problem.
Steps Toward Deep Kernel Methods from Infinite Neural Networks
Contemporary deep neural networks exhibit impressive results on practical problems.
Congruency-Based Reranking
The utility of the tool is demonstrated within the context of visual search of documents from the Cairo Genizah and for retrieval of paintings by the same artist and in the same style.
Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions
In this work we develop efficient methods for learning random MAP predictors for structured label problems.
On Measure Concentration of Random Maximum A-Posteriori Perturbations
Applying the general result to MAP perturbations can yield a more efficient algorithm to approximate sampling from the Gibbs distribution.
On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations
In this paper we describe how MAP inference can be used to sample efficiently from Gibbs distributions.
Globally Convergent Dual MAP LP Relaxation Solvers using Fenchel-Young Margins
While finding the exact solution for the MAP inference problem is intractable for many real-world tasks, MAP LP relaxations have been shown to be very effective in practice.
Blending Learning and Inference in Structured Prediction
In this paper we derive an efficient algorithm to learn the parameters of structured predictors in general graphical models.
Direct Loss Minimization for Structured Prediction
In discriminative machine learning one is interested in training a system to optimize a certain desired measure of performance, or loss.
A Primal-Dual Message-Passing Algorithm for Approximated Large Scale Structured Prediction
We then propose an intuitive approximation for structured prediction problems using Fenchel duality based on a local entropy approximation that computes the exact gradients of the approximated problem and is guaranteed to converge.
