Search Results for author:
Found 11 papers, 1 papers with code
Toward a Theory of Tokenization in LLMs
In this paper, we investigate tokenization from a theoretical point of view by studying the behavior of transformers on simple data generating processes.
Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits
We consider the sequential decision-making problem where the mean outcome is a non-linear function of the chosen action.
Sample Efficient Deep Reinforcement Learning via Local Planning
One useful property of simulators is that it is typically easy to reset the environment to a previously observed state.
Spectral Regularization Allows Data-frugal Learning over Combinatorial Spaces
Data-driven machine learning models are being increasingly employed in several important inference problems in biology, chemistry, and physics which require learning over combinatorial spaces.
Minimax Optimal Online Imitation Learning via Replay Estimation
In the tabular setting or with linear function approximation, our meta theorem shows that the performance gap incurred by our approach achieves the optimal $\widetilde{O} \left( \min({H^{3/2}} / {N}, {H} / {\sqrt{N}} \right)$ dependency, under significantly weaker assumptions compared to prior work.
On the Value of Interaction and Function Approximation in Imitation Learning
In contrast, when the MDP transition structure is known to the learner such as in the case of simulators, we demonstrate fundamental differences compared to the tabular setting in terms of the performance of an optimal algorithm, Mimic-MD (Rajaraman et al. (2020)) when extended to the function approximation setting.
Semi-supervised Active Regression
In this setting, the learner has access to a dataset $X \in \mathbb{R}^{(n_1+n_2) \times d}$ which is composed of $n_1$ unlabelled examples that an algorithm can actively query, and $n_2$ examples labelled a-priori.
Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally
We establish an upper bound $O(|\mathcal{S}|H^{3/2}/N)$ for the suboptimality using the Mimic-MD algorithm in Rajaraman et al (2020) which we prove to be computationally efficient.
How good is Good-Turing for Markov samples?
In this work, we study convergence of the GT estimator for missing stationary mass (i. e., total stationary probability of missing symbols) of Markov samples on an alphabet $\mathcal{X}$ with stationary distribution $[\pi_x:x \in \mathcal{X}]$ and transition probability matrix (t. p. m.)
FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning
In this paper, we propose a secure aggregation protocol, FastSecAgg, that is efficient in terms of computation and communication, and robust to client dropouts.
Toward the Fundamental Limits of Imitation Learning
Here, we show that the policy which mimics the expert whenever possible is in expectation $\lesssim \frac{|\mathcal{S}| H^2 \log (N)}{N}$ suboptimal compared to the value of the expert, even when the expert follows an arbitrary stochastic policy.
