Search Results for author:
Found 25 papers, 11 papers with code
Fundamental Limits of Perfect Concept Erasure
Concept erasure is the task of erasing information about a concept (e. g., gender or race) from a representation set while retaining the maximum possible utility -- information from original representations.
Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning
Reward-based finetuning is crucial for aligning language policies with intended behaviors (e. g., creativity and safety).
Auctions with LLM Summaries
We study an auction setting in which bidders bid for placement of their content within a summary generated by a large language model (LLM), e. g., an ad auction in which the display is a summary paragraph of multiple ads.
A Minimaximalist Approach to Reinforcement Learning from Human Feedback
Our approach is maximalist in that it provably handles non-Markovian, intransitive, and stochastic preferences while being robust to the compounding errors that plague offline approaches to sequential prediction.
Enhancing Group Fairness in Online Settings Using Oblique Decision Forests
In the online setting, where the algorithm has access to a single instance at a time, estimating the group fairness objective requires additional storage and significantly more computation (e. g., forward/backward passes) than the task-specific objective at every time step.
Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion
A shortcoming of this approach is that users often do not know which query will provide the best retrieval performance on the current information retrieval system, meaning that any query autocompletion methods trained to mimic user behavior can lead to suboptimal query suggestions.
Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage
Instead, the learner is presented with a static offline dataset of state-action-next state transition triples from a potentially less proficient behavior policy.
Mitigating Covariate Shift in Imitation Learning via Offline Data With Partial Coverage
Instead, the learner is presented with a static offline dataset of state-action-next state triples from a potentially less proficient behavior policy.
Optimism is All You Need: Model-Based Imitation Learning From Observation Alone
This paper studies Imitation Learning from Observations alone (ILFO) where the learner is presented with expert demonstrations that only consist of states encountered by an expert (without access to actions taken by the expert).
MobILE: Model-Based Imitation Learning From Observation Alone
This paper studies Imitation Learning from Observations alone (ILFO) where the learner is presented with expert demonstrations that consist only of states visited by an expert (without access to actions taken by the expert).
Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy
We show that our algorithm has a regret guarantee of $O(k\sqrt{(A-k+1)T \log (|\mathcal{F}|T)})$, where $A$ is the total number of arms and $\mathcal{F}$ is the class containing the regression function, while only requiring $\tilde{O}(A)$ computation per time step.
Computational Efficiency
Extreme Multi-Label Classification
+3
Making Paper Reviewing Robust to Bid Manipulation Attacks
We develop a novel approach for paper bidding and assignment that is much more robust against such attacks.
MOReL: Model-Based Offline Reinforcement Learning
In this work, we present MOReL, an algorithmic framework for model-based offline RL.
MOReL : Model-Based Offline Reinforcement Learning
In this work, we present MOReL, an algorithmic framework for model-based offline RL.
Rethinking learning rate schedules for stochastic optimization
One plausible explanation is that non-convex neural network training procedures are better suited to the use of fundamentally different learning rate schedules, such as the ``cut the learning rate every constant number of epochs'' method (which more closely resembles an exponentially decaying learning rate schedule); note that this widely used schedule is in stark contrast to the polynomial decay schemes prescribed in the stochastic approximation literature, which are indeed shown to be (worst case) optimal for classes of convex optimization problems.
The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares
First, this work shows that even if the time horizon T (i. e. the number of iterations SGD is run for) is known in advance, SGD's final iterate behavior with any polynomially decaying learning rate scheme is highly sub-optimal compared to the minimax rate (by a condition number factor in the strongly convex case and a factor of $\sqrt{T}$ in the non-strongly convex case).
On the insufficiency of existing momentum schemes for Stochastic Optimization
Extensive empirical results in this paper show that ASGD has performance gains over HB, NAG, and SGD.
Leverage Score Sampling for Faster Accelerated Regression and ERM
Given a matrix $\mathbf{A}\in\mathbb{R}^{n\times d}$ and a vector $b \in\mathbb{R}^{d}$, we show how to compute an $\epsilon$-approximate solution to the regression problem $ \min_{x\in\mathbb{R}^{d}}\frac{1}{2} \|\mathbf{A} x - b\|_{2}^{2} $ in time $ \tilde{O} ((n+\sqrt{d\cdot\kappa_{\text{sum}}})\cdot s\cdot\log\epsilon^{-1}) $ where $\kappa_{\text{sum}}=\mathrm{tr}\left(\mathbf{A}^{\top}\mathbf{A}\right)/\lambda_{\min}(\mathbf{A}^{T}\mathbf{A})$ and $s$ is the maximum number of non-zero entries in a row of $\mathbf{A}$.
Efficient Estimation of Generalization Error and Bias-Variance Components of Ensembles
We also demonstrate their usefulness in making design choices such as the number of classifiers in the ensemble and the size of a subset of data used for training that is needed to achieve a certain value of generalization error.
A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares)
This work provides a simplified proof of the statistical minimax optimality of (iterate averaged) stochastic gradient descent (SGD), for the special case of least squares.
Accelerating Stochastic Gradient Descent For Least Squares Regression
There is widespread sentiment that it is not possible to effectively utilize fast gradient methods (e. g. Nesterov's acceleration, conjugate gradient, heavy ball) for the purposes of stochastic optimization due to their instability and error accumulation, a notion made precise in d'Aspremont 2008 and Devolder, Glineur, and Nesterov 2014.
Parallelizing Stochastic Gradient Descent for Least Squares Regression: mini-batching, averaging, and model misspecification
In particular, this work provides a sharp analysis of: (1) mini-batching, a method of averaging many samples of a stochastic gradient to both reduce the variance of the stochastic gradient estimate and for parallelizing SGD and (2) tail-averaging, a method involving averaging the final few iterates of SGD to decrease the variance in SGD's final iterate.
Submodular Hamming Metrics
We show that there is a largely unexplored class of functions (positive polymatroids) that can define proper discrete metrics over pairs of binary vectors and that are fairly tractable to optimize over.
A Quantitative Evaluation Framework for Missing Value Imputation Algorithms
We consider the problem of quantitatively evaluating missing value imputation algorithms.
A Structured Prediction Approach for Missing Value Imputation
In this paper we propose a structured output approach for missing value imputation that also incorporates domain constraints.
