betaFeedback

WorksComputer Science

AgileRate: Bringing Adaptivity and Robustness to DeFi Lending Markets

Abstract

Decentralized Finance (DeFi) has revolutionized lending by replacing intermediaries with algorithm-driven liquidity pools. However, existing platforms like Aave and Compound rely on static interest rate curves and collateral requirements that struggle to adapt to rapid market changes, leading to inefficiencies in utilization and increased risks of liquidations. In this work, we propose a dynamic model of the lending market based on evolving demand and supply curves, alongside an adaptive interest rate controller that responds in real-time to shifting market conditions. Using a Recursive Least Squares algorithm, our controller tracks the external market and achieves stable utilization, while also controlling default and liquidation risk. We provide theoretical guarantees on the interest rate convergence and utilization stability of our algorithm. We establish bounds on the system's vulnerability to adversarial manipulation compared to static curves, while quantifying the trade-off between adaptivity and adversarial robustness. We propose two complementary approaches to mitigating adversarial manipulation: an algorithmic method that detects extreme demand and supply fluctuations and a market-based strategy that enhances elasticity, potentially via interest rate derivative markets. Our dynamic curve demand/supply model demonstrates a low best-fit error on Aave data, while our interest rate controller significantly outperforms static curve protocols in maintaining optimal utilization and minimizing liquidations.

Introduction

Lending markets in DeFi Decentralized Finance (DeFi) has transformed lending by eliminating centralized intermediaries such as banks, replacing them with transparent, algorithm-driven liquidity pools. Platforms such as Aave [4] and Compound [19] enable lenders to provide the capital that borrowers can access by pledging collateral. A key goal of these protocols is to maintain stable utilization rates, adjusting interest rates to balance supply and demand [27]. Low utilization results in lower interest rates to encourage borrowing, while increased utilization drives up rates to manage liquidity. Another critical parameter is the collateral factor, which ensures that the risk of borrowing is minimized while the markets remain attractive. Setting appropriate collateral levels requires evaluating recent price behavior of the collateral asset and the lender’s risk tolerance [37].

Current approaches Current DeFi platforms determine interest rates based on a static function of utilization [3, 18]. This approach uses utilization to represent supply/demand dynamics, market risk, and attractiveness, relying on a manually set, arbitrary interest rate curve. Additionally, collateral factors in these markets are established through a thorough process involving community proposals and reviews [2, 17], which are voted on every few months or so.

Challenges in adapting to market conditions Current DeFi systems are slow to adapt to rapid market changes, leading to potential losses and increased risks due to delayed parameter adjustments, particularly during major price fluctuations. For instance, between August 1 and August 6, 2024, Aave ETH V3 experienced over $116M in liquidations due to a significant price drop in ETH. Among the affected users, only 45% ($53M) actively increased their collateral just before being liquidated. It turns out that a 15% increase in the over-collateralization ratio could have nearly halved the number of liquidations for these users (see Figure 1b). However, Aave’s slow response in adjusting collateral ratios and liquidation thresholds failed to avert these outcomes. Additionally, Aave has faced challenges in maintaining optimal utilization levels during rapid, unforeseen market changes, particularly when demand spikes due to new yield farming opportunities or similar events. For example, Figure 1a illustrates the utilization of the Aave LUSD-ETH pool during a period of significant volatility in LUSD demand, driven by unstable yield farming opportunities. Although the protocol aims to maintain a target utilization of 0.8, it frequently fails to achieve this target, with deviations persisting for extended periods.

Figure 1a. Lending platforms fail to adapt to market demand and supply changes

Figure 1b. A slight increase in the collateral ratio could have reduced liquidations

Modeling markets and adaptive lending pools The first challenge in designing a better lending protocols is to model the existing population of DeFi lenders and borrowers. We start this work by proposing a model based on changing demand and supply curves with noise (§ 2). We define an optimal interest rate controller to be the one that sets the rate exactly equal to the equilibrium rate that realizes the desired utilization given the current market conditions. Our goal is to design an optimally adaptive lending protocol for this model, and to quantify the agility with which the protocol can change based on external market conditions.

Adaptivity versus robustness Introducing adaptivity into a protocol can increase its vulnerability to manipulation [32], as an adaptive protocol adjusts based on recent market activities, learning from the trades made by borrowers and lenders. However, an adversary can exploit this by distorting the historical trade data, making the protocol respond to false shifts in demand or supply. Therefore, it is crucial to quantify the tradeoff between adaptivity and adversarial robustness before deploying any new lending protocol. Specifically, we assess how much the interest rate can be manipulated when an adversary controls a portion of the total demand and supply. We suggest two solutions each operating in a different scale, to mitigate the adversarial manipulations.

The following section summarizes our results. We set the broader research context in which we make these contributions in Appendix [§ 10.§ 1].

Our Contributions

Dynamic model and evaluation metrics: (§ 2) We propose a dynamic model of the lending market via evolving demand and supply curves for the lent asset. We introduce three core metrics to evaluate DeFi lending platforms, focusing on targeting a specific utilization, liquidation/default risk, and the robustness of the protocol to adversarial manipulations.

Agile interest rate controller: (§ 3.1) We propose an adaptive interest rate controller that adjusts dynamically based on real-time market conditions, ensuring a desired stable utilization in presence of changing environments. The market conditions are estimated in an online manner, using a variant of the Recursive Least Squares algorithm. We provide theoretical guarantees on the controller’s convergence speed to the target interest rate. Additionally, we outline how the algorithm can be augmented with a risk minimization controller, which keeps defaults and liquidations below a desired threshold. Bounds on adversarial robustness: (§ 4) We establish theoretical bounds on the manipulability of the interest rate as set by our adaptive protocol and compare it with a bound for a static curve. We show that adaptive protocols can be manipulated arbitrarily in presence of inelastic demand/supply of loans, while the same remains bounded for static protocols.

Enhancing the adversarial robustness: (§ 4.3) We propose two complementary methods to mitigate adversarial manipulation, each addressing the issue from a different perspective. The first is an algorithmic approach based on robust recursive least squares, designed to detect and filter out improbable demand and supply patterns. The second focuses on structural market adjustments that encourage greater user elasticity, strengthening the lending pool’s resilience against adversarial manipulation.

Evaluation: (§ 5) We justify our dynamic demand/supply curve model by fitting it on data from lending pools on Aave, obtaining a 5% best-fit error. We complement the theoretical guarantees of previous sections with empirical tests of the convergence and robustness of our algorithm.

Problem formulation

Market participants and pool mechanics

DeFi lending platforms consist of three main participants: borrowers, lenders, and liquidators, who interact via a smart contract, denoted as P\mathcal{P}. These interactions occur in discrete time slots, each corresponding to a block.

Borrowers Borrowers secure loans by providing collateral in asset Ac\mathcal{A}_{c} to borrow asset Al\mathcal{A}_{l} from a pooled system. The loan amount for borrower ii at time tt is Bt(i)B_{t}(i), with total borrowings BtB_{t}, and their collateral is Ct(i)C_{t}(i), with total collateral CtC_{t}. To open a borrowing position, borrowers must satisfy Bt(i)Ct(i)pt<ct<1\frac{B_{t}(i)}{C_{t}(i)p_{t}} < c_{t} < 1, where ptp_{t} is the price of Ac\mathcal{A}_{c} relative to Al\mathcal{A}_{l}, and ctc_{t} is the protocol-defined collateral factor. The protocol applies a global interest rate rtr_{t} to all borrowings, increasing BtB_{t} over time.

Lenders Lenders deposit Al\mathcal{A}_{l} to earn interest from borrowers. Unlike many platforms that reserve interest for risk funds and token rewards [4, 19], this protocol distributes all accrued interest to lenders, making them directly bear default risks. Let Lt(i)L_{t}(i) be lender ii’s deposit and LtL_{t} be the total deposits, with utilization rate Ut=BtLtU_{t} = \frac{B_{t}}{L_{t}}. Lenders earn interest at rtr_{t} on borrowed funds, and in case of default, losses are proportional to their deposits.

Liquidators To prevent risks from falling collateral prices, a liquidation mechanism allows third-party liquidators to intervene when a borrower’s loan-to-value (LTV) ratio exceeds the liquidation threshold LTt<1LT_{t} < 1. A liquidator repays part of the borrower’s debt in Al\mathcal{A}_{l}, claims a corresponding amount of Ac\mathcal{A}_{c}, and earns an incentive fee LItLI_{t}. Liquidations continue until the LTV ratio falls below the liquidation threshold LTtLT_{t}.

Protocol (P\mathcal{P}) The protocol is encoded in the smart contract and dictates the pool parameters {rt,ct,LTt,LIt}\{r_{t}, c_{t}, LT_{t}, LI_{t}\} for each timeslot, following predetermined rules. The smart contract also provides an interface for users to interact with the pool under these conditions.

Asset price model

We model the system in discrete time intervals, normalized to the block time. The price of the collateral asset ptp_{t} is tracked from block to block, while the lent asset, Al\mathcal{A}_{l}, is assumed to be a stablecoin with minimal price fluctuation. The collateral asset price ptp_{t} follows an exogenous geometric Brownian motion with stochastic volatility σt\sigma_{t}, based on the Heston model [26].

σt2=σt−12+κ(θ−σt−12)+ξσt−1ηt,ηt∼N(0,1)(1)\sigma_t^2 = \sigma_{t-1}^2 + \kappa(\theta- \sigma_{t-1}^2) + \xi\sigma_{t-1}\eta_t,\qquad\eta_t \sim\mathcal{N}(0,1) \tag*{(1)}
pt=pt−1exp⁡((μ−σt22)+σtεt),εt∼N(0,1)(2)p_t = p_{t-1}\exp\left(\left(\mu- \frac{\sigma_t^2}{2}\right) + \sigma_t\varepsilon_t\right),\qquad\varepsilon_t \sim\mathcal{N}(0,1) \tag*{(2)}

Here, μ\mu is the drift, σt\sigma_t is the stochastic volatility, κ\kappa is the mean-reversion rate, θ\theta is the long-term volatility mean, ξ\xi represents the volatility of volatility, ηt\eta_t is a normal random variable for the volatility process, and εt\varepsilon_t is a normal random variable for the asset price.

Users' incentives

Each borrower (lender) ii is specified with their time varying demand (supply) capacity denoted by Bt(i)B_t(i) (Lt(i)L_t(i)) and their private value rtb(i)r_t^b(i) (rtl(i)r_t^l(i)), representing the maximum (minimum) interest rate they are willing to pay (receive from) P\mathcal{P} to remain engaged without seeking alternative markets. The rates rtb(i)r_t^b(i) and rtl(i)r_t^l(i), referred to as external interest rates in this paper, represent the rates that alternative markets with comparable risk to P\mathcal{P} would offer to borrower (or lender) ii. We represent the vector consisting of all borrowers (lenders) external rate by r^tb\hat{\mathbf{r}}_t^b (r^tl\hat{\mathbf{r}}_t^l) and their capacity vector respectively by B^t\hat{\mathbf{B}}_t (L^t\hat{\mathbf{L}}_t).

Truthful vs strategic Borrower (Lender) ii is considered truthful if, at any given time tt and given the interest rate rtr_t set by P\mathcal{P}, they borrow (lend) to their maximum capacity i.e., Bt(i)B_t(i) (Lt(i)L_t(i)) if and only if rt≤rtb(i)r_t \leq r_t^b(i) (rtUt≥rtl(i)r_t U_t \geq r_t^l(i)). Any borrower/lender who deviates from this strategy is considered strategic.

True demand/supply curve The true demand curve is the total demand at interest rate rr when all the borrowers are truthful, this function is parameterized by the external interest rate and capacity of the borrowers collectively denoted by Bt:={B^t,r^tb}\mathcal{B}_t := \{\hat{\mathbf{B}}_t,\hat{\mathbf{r}}_t^b\}:

f(r;Bt):=∑iBt(i)1(rtb(i)≥r)(3)f(r;\mathcal{B}_t) := \sum_i B_t(i)\mathbf{1}_{(r_t^b(i)\geq r)} \tag*{(3)}

Similarly, the true supply curve represents the total supply at an effective interest rate when all the lenders are truthful; suppliers’ effective rate is the interest rate they receive on the utilized part of the pool i.e., reff:=r⋅Ur_{\mathrm{eff}} := r \cdot U. The supply function is parameterized by the external interest rate and capacity of the lenders collectively denoted by L:={L^t,r^tl}\mathcal{L} := \{\hat{\mathbf{L}}_t,\hat{\mathbf{r}}_t^l\}:

g(reff;Lt):=∑iLt(i)1(rtl(i)≤reff)(4)g(r_{\mathrm{eff}};\mathcal{L}_t) := \sum_i L_t(i)\mathbf{1}_{(r_t^l(i)\leq r_{\mathrm{eff}})} \tag*{(4)}

Utility function Strategic lenders and borrowers decide how much to allocate to the protocol versus external markets based on their expected returns. A strategic lender ii will allocate some portion of their supply, L^t(i)\hat{L}_t(i), to the protocol while placing the rest in an external market offering a rate rtl(i)r_t^l(i). The lender’s goal is to maximize their overall returns from both sources over time. Similarly, a strategic borrower ii selects how much to borrow, B^t(i)\hat{B}_t(i), to minimize their overall borrowing costs. Calculating these optimal decisions can be quite complex, so we simplify the utility functions in certain cases to better analyze user behavior within the protocol.

At any time tt, a strategic lender ii allocates a portion (or potentially all) of their supply L^t(i)≤Lt(i)\hat{L}_t(i) \leq L_t(i) to P\mathcal{P} and allocate the remaining supply, Lt(i)−L^t(i)L_t(i) - \hat{L}_t(i), to an alternative external market that offers a rate rtl(i)r_t^l(i). The lender’s objective is to maximize cumulative utility over time, derived from expected interest rates from both P\mathcal{P} and the alternative market. Formally, the cumulative utility over time for the lender is expressed as:

E[∑t=0∞(L^t(i)rtUt+(Lt(i)−L^t(i))rtl(i))](5)\mathbb{E}\left[\sum_{t=0}^{\infty}\left(\hat{L}_{t}(i)r_{t}U_{t}+\left(L_{t}(i)-\hat{L}_{t}(i)\right)r_{t}^{l}(i)\right)\right] \tag*{(5)}

Here, the expectation is taken over the randomness of protocol and the stochastic nature of the users’ behaviour which in turn impact the pool’s state and P\mathcal{P}’s decisions. Similarly, a borrower ii aims to choose their demand value B^t(i)≤Bt(i)\hat{B}_{t}(i)\leq B_{t}(i) to minimize the sum of the expected interest rate paid over time, which can be formalized as:

E[∑t=0∞(B^t(i)rt+(Bt(i)−B^t(i))rtb(i))](6)\mathbb{E}\left[\sum_{t=0}^{\infty}\left(\hat{B}_{t}(i)r_{t}+\left(B_{t}(i)-\hat{B}_{t}(i)\right)r_{t}^{b}(i)\right)\right] \tag*{(6)}

However, calculating these utility functions and determining the sequences {L^t(i)}t\{\hat{L}_{t}(i)\}_{t} and {B^t(i)}t\{\hat{B}_{t}(i)\}_{t} that optimize them can be highly complex and may not lead to truthful strategies. In this paper, whenever needed, we simplify these utility functions for specific protocols and user behavior scenarios.

Protocol objectives

We define the protocol objectives in a three-fold manner. The explicit mathematical definitions we use for these objectives are given in Appendix [§ 10.§ 2].

References

  1. [1][n.d.]. https://users.ssc.wisc.edu/~dquint/econ805%202009/lectures/econ%20805%20lecture%2016.pdf
  2. [2]aaveGov [n. d.]. Aave Finance Governance. https://app.aave.com/governance/. Accessed: 2023-05.
  3. [3]aaveIR [n. d.]. Interest rate curve in aave. https://docs.aave.com/risk/liquidity-risk/borrow-interest-rate. Accessed: 2023-05.
  4. [4]aaveWP [n. d.]. Aave Whitepaper. https://github.com/aave/aave-protocol/blob/master/docs/Aave_Protocol_Whitepaper_v1_0.pdf. Accessed: 2024-02.
  5. [5]ajna [n. d.]. Ajna Whitepaper. https://www.ajna.finance/pdf/Ajna_Protocol_Whitepaper_01-11-2024.pdf. Accessed: 2023-05.
  6. [6]Mahsa Bastankhah, Viraj Nadkarni, Chi Jin, Sanjeev Kulkarni, and Pramod Viswanath. 2024. Thinking Fast and Slow: Data-Driven Adaptive DeFi Borrow-Lending Protocol. In 6th Conference on Advances in Financial Technologies (AFT 2024) (Leibniz International Proceedings in Informatics (LIPIcs), Vol. 316), Rainer Böhme and Lucianna Kiffer (Eds.). Schloss Dagstuhl – Leibniz-Zentrum für Informatik, Dagstuhl, Germany, 27:1–27:23. https://doi.org/10.4230/LIPIcs.AFT.2024.27
  7. [7]Kush Bhatia, Prateek Jain, and Purushottam Kar. 2015. Robust regression via hard thresholding. Advances in neural information processing systems 28 (2015).arxiv.org/abs/1506.02428
  8. [8]Darren Camas, Mauricio Hernandes, and Dimitar Dinev. 2021. IPOR: an Inter-protocol Offered Rate for Decentralized Finance. https://docs.ipor.io/research-whitepapers/white-paper
  9. [9]Rafael M Canetti and Martin D Espańa. 1989. Convergence analysis of the least-squares identification algorithm with a variable forgetting factor for time-varying linear systems. Automatica 25, 4 (1989), 609–612.DOI
  10. [10]Sylvain Carre and Franck Gabriel. 2023. Security and Efficiency in DeFi Lending. Université Paris-Dauphine Research Paper 4307207 (2023).DOI
  11. [11]Yuk-Shee Chan and George Kanatas. 1985. Asymmetric valuations and the role of collateral in loan agreements. Journal of money, credit and banking 17, 1 (1985), 84–95.DOI
  12. [12]Sitan Chen, Frederic Koehler, Ankur Moitra, and Morris Yau. 2022. Kalman filtering with adversarial corruptions. In Proceedings of the 54th Annual ACM SIGACT Symposium on Theory of Computing. 832–845.arxiv.org/abs/2111.06395
  13. [13]Tarun Chuth, Peteris Erins, and Kshitij Kulkarni. 2023. Attacks on Dynamic DeFi Interest Rate Curves. arXiv preprint arXiv:2307.13139 (2023).
  14. [14]Jonathan Chiu, Emre Ozdenoren, Kathy Yuan, and Shengxing Zhang. 2022. On the fragility of defi lending. Available at SSRN 4328481 (2022).
  15. [15]Samuel N Cohen, Marc Sabate-Vidales, Lukasz Szpruch, and Mathis Gontier Delaunay. 2023. The paradox of adversarial liquidation in decentralised lending. Available at SSRN 4540333 (2023).DOI
  16. [16]Samuel N Cohen, Leandro Sánchez-Betancourt, and Lukasz Szpruch. 2023. The Economics of Interest Rate Models in Decentralised Lending Protocols. Available at SSRN (2023).
  17. [17]compoundGov [n. d.]. Compound Finance Governance. https://compound.finance/governance. Accessed: 2023-05.
  18. [18]compoundIR [n. d.]. Impermanent loss in defi lending. https://docs.compound.finance/interest-rates/. Accessed: 2023-05.
  19. [19]compoundWP [n. d.]. Compound Whitepaper. https://compound.finance/documents/Compound.Whitepaper.pdf. Accessed: 2024-02.
  20. [20]Richard Engelbrecht-Wiggans and Charles M Kahn. 1998. Multi-unit auctions with uniform prices. Economic theory 12 (1998), 227–258.
  21. [21]Pendle Finance. 2022. Pendle Protocol Whitepaper. https://docs.pendle.finance/Introduction
  22. [22]Mohak Goyal, Geoffrey Ramseyer, Ashish Goel, and David Mazières. 2023. Finding the Right Curve: Optimal Design of Constant Function Market Makers. arXiv:2212.03340 [cs.GT]arxiv.org/abs/2212.03340
  23. [23]Gauntlet Research Group. 2025. Aave Market Risk Analysis. Technical Report. Gauntlet. Available at: https://gauntlet.network/reports/aave (Accessed on 2025-01-28).
  24. [24]Gauntlet Research Group. 2025. Compound Market Risk Analysis. Technical Report. Gauntlet. Available at: https://assets-global.website-files.com/648bdc0d4b8ce322f27da0af/651f146b6a1c8cc78e6c9cac_Gauntlet-Compound-Market-Risk-Assessment.pdf (Accessed on 2025-01-28).
  25. [25]Instadapp Guides. 2025. Compound V3 Explained. Available at https://guides.instadapp.io/protocols/compound/compound-v3-explained.
  26. [26]Steven L. Heston. 1993. A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency Options. The Review of Financial Studies 6, 2 (1993), 327–343. http://www.jstor.org/stable/2962057
  27. [27]irThumbRule [n. d.]. Interest rates in decentralised finance. https://www.banque-france.fr/en/publications-and-statistics/publications/interest-rates-decentralised-finance. Accessed: 2023-05.
  28. [28]Syed Aseem Ul Islam and Dennis R Benstein. 2019. Recursive least squares for real-time implementation [lecture notes]. IEEE Control Systems Magazine 39, 3 (2019), 82–85.DOI
  29. [29]Branko Kovačević, Zoran Banjac, and Ivana Kostić Kovačević. 2016. Robust adaptive filtering using recursive weighted least squares with combined scale and variable forgetting factors. EURASIP journal on advances in signal processing 2016 (2016), 1–22.
  30. [30]Jason Milionis, Ciamac C. Moallemi, and Tim Roughgarden. 2023. Automated Market Making and Arbitrage Profits in the Presence of Fees. arXiv:2305.14604 [q-fin.MF]
  31. [31]morpho [n. d.]. Morpho Whitepaper. https://whitepaper.morpho.xyz/. Accessed: 2023-05.
  32. [32]msGauntletLending23 [n. d.]. Making Sense of the DeFi Lending Meta. https://www.gauntlet.xyz/resources/making-sense-of-the-defi-lending-meta. Accessed: 2024-02.
  33. [33]Viraj Nadkarni, Jiachen Hu, Ranvir Rana, Chi Jin, Sanjeev Kulkarni, and Pramod Viswanath. 2023. ZeroSwap: Data-driven Optimal Market Making in DeFi. arXiv preprint arXiv:2310.09413 (2023).arxiv.org/abs/2310.09413
  34. [34]Viraj Nadkarni, Sanjeev Kulkarni, and Pramod Viswanath. 2024. Adaptive Curves for Optimally Efficient Market Making. In 6th Conference on Advances in Financial Technologies (AFT 2024) (Leibniz International Proceedings in Informatics (LIPIcs), Vol. 316), Rainer Böhme and Lusianna Kiffer (Eds.). Schloss Dagstuhl – Leibniz-Zentrum für Informatik, Dagstuhl, Germany, 25:1–25:22. https://doi.org/10.4230/LIPIcs.AFT.2024.25
  35. [35]Ricsson Ngo. 2022. Timeswap V2: Decentralized and Oracle-less Fixed Time Preference Protocol. https://timeswap.io/whitepaper.pdf
  36. [36]Constantin Paleologou, Jacob Benesty, and Silviu Ciochina. 2008. A robust variable forgetting factor recursive least-squares algorithm for system identification. IEEE Signal Processing Letters 15 (2008), 597–600.DOI
  37. [37]riskColDeFi [n. d.]. Navigating Risks in DeFi Lending. https://medium.com/intotheblock/navigating-risks-in-defi-lending-a034dbf83b54. Accessed: 2023-05.
  38. [38]Thomas J Rivera, Fahad Saleh, and Quentin Vandeweyer. 2023. Equilibrium in a DeFi Lending Market. Available at SSRN 4389890 (2023).DOI
  39. [39]Kanis Saengchote. 2023. Decentralized lending and its users: Insights from Compound. Journal of International Financial Markets, Institutions and Money 87 (2023), 101807. https://doi.org/10.1016/j.intfin.2023.101807
  40. [40]Ali H Sayed and Thomas Kailath. 1994. A state-space approach to adaptive RLS filtering. IEEE signal processing magazine 11, 3 (1994), 18–60.
  41. [41]Dan Simon. 2006. Optimal state estimation: Kalman, H infinity, and nonlinear approaches. John Wiley & Sons.
  42. [42]Joseph E Stiglitz and Andrew Weiss. 1981. Credit rationing in markets with imperfect information. The American economic review 71, 3 (1981), 393–410.
  43. [43]Jo-Anne Ting, Hannes Theodorou, and Stefan Schaal. 2007. Learning an outlier-robust Kalman filter. In Machine Learning: ECML 2007: 18th European Conference on Machine Learning, Warsaw, Poland, September 17-21, 2007. Proceedings 18. Springer, 748–756.
  44. [44]Aviv Vaish, Maya Dotan, Kaihua Qin, Aviv Zohar, and Arthur Gervais. 2023. Suboptimality in defi. Cryptology ePrint Archive (2023).
  45. [45]Stephan Zheng, Alexander Trott, Sunil Srinivasa, David C. Parkes, and Richard Socher. 2021. The AI Economist: Optimal Economic Policy Design via Two-level Deep Reinforcement Learning. CoRR abs/2108.02755 (2021). arXiv:2108.02755 https://arxiv.org/abs/2108.02755
  46. [46]Yuexian Zou, SC Chan, and Tung-Sang Ng. 2000. A recursive least M-estimate (RLM) adaptive filter for robust filtering in impulse noise. IEEE Signal Processing Letters 7, 11 (2000), 324–326.DOI

Paper details

vlnc:W_dh9yqjbz
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 2

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Computer Science

Not recorded for this paper

View statement
Looking for related papers…
Contents