Publications (24)
Thompson Sampling for Noncompliant Bandits
Andrew Stirn, Tony Jebara
Thompson sampling, a Bayesian method for balancing exploration and exploitation in bandit problems, has theoretical guarantees and exhibits strong empirical performance in many dom…
Stochastic Bound Majorization
Anna Choromanska, Tony Jebara
Recently a majorization method for optimizing partition functions of log-linear models was proposed alongside a novel quadratic variational upper-bound. In the batch setting, it ou…
Bethe Bounds and Approximating the Global Optimum
Adrian Weller, Tony Jebara
Inference in general Markov random fields (MRFs) is NP-hard, though identifying the maximum a posteriori (MAP) configuration of pairwise MRFs with submodular cost functions is effi…
Correlated Variational Auto-Encoders
Da Tang, Dawen Liang, Tony Jebara +1
Variational Auto-Encoders (VAEs) are capable of learning latent representations for high dimensional data. However, due to the i.i.d. assumption, VAEs only optimize the singleton v…
A New Distribution on the Simplex with Auto-Encoding Applications
Andrew Stirn, Tony Jebara, David A Knowles
We construct a new distribution for the simplex using the Kumaraswamy distribution and an ordered stick-breaking process. We explore and develop the theoretical properties of this…
Bethe Learning of Conditional Random Fields via MAP Decoding
Kui Tang, Nicholas Ruozzi, David Belanger +1
Many machine learning tasks can be formulated in terms of predicting structured outputs. In frameworks such as the structured support vector machine (SVM-Struct) and the structured…
Binary embeddings with structured hashed projections
Anna Choromanska, Krzysztof Choromanski, Mariusz Bojarski +3
We consider the hashing mechanism for constructing binary embeddings, that involves pseudo-random projections followed by nonlinear (sign function) mappings. The pseudo-random proj…
A Unified Language Model for Large Scale Search, Recommendation, and Reasoning
Marco De Nadai, Edoardo D'Amico, Max Lefarov +18
LLMs are increasingly applied to recommendation, retrieval, and reasoning, yet deploying a single end-to-end model that can jointly support these behaviors over large, heterogeneou…
On Learning from Label Proportions
Felix X. Yu, Krzysztof Choromanski, Sanjiv Kumar +2
Learning from Label Proportions (LLP) is a learning setting, where the training data is provided in groups, or "bags", and only the proportion of each class in each bag is known. T…
A refinement of Bennett's inequality with applications to portfolio optimization
Tony Jebara
A refinement of Bennett's inequality is introduced which is strictly tighter than the classical bound. The new bound establishes the convergence of the average of independent rando…
Learning Correlated Latent Representations with Adaptive Priors
Da Tang, Dawen Liang, Nicholas Ruozzi +1
Variational Auto-Encoders (VAEs) have been widely applied for learning compact, low-dimensional latent representations of high-dimensional data. When the correlation structure amon…
Item Recommendation with Variational Autoencoders and Heterogenous Priors
Giannis Karamanolakis, Kevin Raji Cherian, Ananth Ravi Narayan +3
In recent years, Variational Autoencoders (VAEs) have been shown to be highly effective in both standard collaborative filtering applications and extensions such as incorporation o…
Frank-Wolfe Algorithms for Saddle Point Problems
Gauthier Gidel, Tony Jebara, Simon Lacoste-Julien
We extend the Frank-Wolfe (FW) optimization algorithm to solve constrained smooth convex-concave saddle point (SP) problems. Remarkably, the method only requires access to linear m…
Coloring tournaments with forbidden substructures
Krzysztof Choromanski, Tony Jebara
Coloring graphs is an important algorithmic problem in combinatorics with many applications in computer science. In this paper we study coloring tournaments. A chromatic number of…
Approximating the Bethe partition function
Adrian Weller, Tony Jebara
When belief propagation (BP) converges, it does so to a stationary point of the Bethe free energy , and is often strikingly accurate. However, it may converge only to a local op…
SVM for learning with label proportions
Felix X. Yu, Dong Liu, Sanjiv Kumar +2
We study the problem of learning with label proportions in which the training data is provided in groups and only the proportion of each class in each group is known. We propose a…
Variational Autoencoders for Collaborative Filtering
Dawen Liang, Rahul G. Krishnan, Matthew D. Hoffman +1
We extend variational autoencoders (VAEs) to collaborative filtering for implicit feedback. This non-linear probabilistic model enables us to go beyond the limited modeling capacit…
Beta Survival Models
David Hubbard, Benoit Rostykus, Yves Raimond +1
This article analyzes the problem of estimating the time until an event occurs, also known as survival modeling. We observe through substantial experiments on large real-world data…
Selectively Contextual Bandits
Claudia Roberts, Maria Dimakopoulou, Qifeng Qiao +2
Contextual bandits are widely used in industrial personalization systems. These online learning frameworks learn a treatment assignment policy in the presence of treatment effects…
Active Multitask Learning with Committees
Jingxi Xu, Da Tang, Tony Jebara
The cost of annotating training data has traditionally been a bottleneck for supervised learning approaches. The problem is further exacerbated when supervised learning is applied…
Approximating the Permanent with Belief Propagation
Bert Huang, Tony Jebara
This work describes a method of approximating matrix permanents efficiently using belief propagation. We formulate a probability distribution whose partition function is exactly th…
Subgoal Discovery for Hierarchical Dialogue Policy Learning
Da Tang, Xiujun Li, Jianfeng Gao +3
Developing agents to engage in complex goal-oriented dialogues is challenging partly because the main learning signals are very sparse in long conversations. In this paper, we prop…
Semistochastic Quadratic Bound Methods
Aleksandr Y. Aravkin, Anna Choromanska, Tony Jebara +1
Partition functions arise in a variety of settings, including conditional random fields, logistic regression, and latent gaussian models. In this paper, we consider semistochastic…
Initialization and Coordinate Optimization for Multi-way Matching
Da Tang, Tony Jebara
We consider the problem of consistently matching multiple sets of elements to each other, which is a common task in fields such as computer vision. To solve the underlying NP-hard…